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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .HCM
    -0.07
     brun
    -0.06
    -HT
    -0.06
     �
    -0.06
     зим
    -0.06
    OfBirth
    -0.06
    labilir
    -0.06
     oste
    -0.06
    IFO
    -0.05
     JDK
    -0.05
    POSITIVE LOGITS
     Rating
    0.08
    aint
    0.07
     loss
    0.07
    _NON
    0.07
    .al
    0.07
    olatile
    0.06
    tons
    0.06
    oker
    0.06
    ks
    0.06
    cast
    0.06
    Act Density 0.982%

    No Known Activations