Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    maps data

    np_max-act · gemini-2.0-flash

    This neuron responds to technical descriptions of an autoencoder’s architecture and mapping functions (e.g. mentions of encoder/decoder, latent‐space encoding, and data reconstruction).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .xaxis
    -0.07
     TEM
    -0.06
    *x
    -0.06
     confidentiality
    -0.06
    Leaders
    -0.06
     functional
    -0.06
     expiresIn
    -0.06
     �
    -0.06
     populated
    -0.06
     folding
    -0.06
    POSITIVE LOGITS
    τής
    0.07
     Dangerous
    0.07
    district
    0.07
    ング
    0.07
     penetrated
    0.07
     Cumberland
    0.07
    стика
    0.07
    .uf
    0.07
     VE
    0.06
    dek
    0.06
    Act Density 0.021%

    No Known Activations