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

    Neuronpedia

    INDEX
    Explanations

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Current
    -0.06
    addin
    -0.06
     Paradise
    -0.06
    962
    -0.06
     NotImplementedException
    -0.06
     Sez
    -0.06
    408
    -0.06
    üst
    -0.06
    auce
    -0.06
    internal
    -0.06
    POSITIVE LOGITS
     fert
    0.07
     sortie
    0.07
    ोड़
    0.07
    ceiving
    0.06
    flare
    0.06
    TRANSFER
    0.06
    .screen
    0.06
     update
    0.06
    IRTH
    0.06
     thirty
    0.06
    Act Density 0.011%

    No Known Activations