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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NB
    -0.07
    urchase
    -0.07
     calls
    -0.06
     regist
    -0.06
    νο
    -0.06
    .token
    -0.06
    &a
    -0.06
     способом
    -0.06
     Verification
    -0.06
     newcom
    -0.06
    POSITIVE LOGITS
     squirt
    0.07
    _normals
    0.06
    _translation
    0.06
    주는
    0.06
     žádné
    0.06
    Gab
    0.06
    +Sans
    0.06
     phòng
    0.06
     �
    0.06
    римін
    0.06
    Act Density 0.040%

    No Known Activations