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

    Neuronpedia

    INDEX
    Explanations

    AWS regions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pottery
    -0.07
     Walls
    -0.07
     reviewer
    -0.07
     Kul
    -0.06
     mạng
    -0.06
    .Static
    -0.06
     neboť
    -0.06
    แ
    -0.06
    (Entity
    -0.06
    fly
    -0.06
    POSITIVE LOGITS
    �
    0.07
     joked
    0.06
     Decomp
    0.06
    (success
    0.06
    /st
    0.06
    .black
    0.06
     Sunshine
    0.06
    Meet
    0.06
     perhaps
    0.06
     weakening
    0.06
    Act Density 0.006%

    No Known Activations