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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Instruments
    -0.08
     बो
    -0.07
    -striped
    -0.07
     pocket
    -0.07
    igkeiten
    -0.07
     striped
    -0.07
     subtitle
    -0.07
     sanctioned
    -0.07
    -pocket
    -0.07
    (Edit
    -0.07
    POSITIVE LOGITS
    .inputs
    0.11
    _relu
    0.10
     neurotrans
    0.10
    _activation
    0.10
    Activation
    0.10
    (inputs
    0.10
    inputs
    0.09
     Activation
    0.09
    relu
    0.09
    _FORWARD
    0.09
    Act Density 0.005%

    No Known Activations