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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subscription
    -0.08
     defaulted
    -0.07
     Claw
    -0.07
    Rooms
    -0.07
    ASCII
    -0.07
     rozší
    -0.07
    /ag
    -0.07
     Neighborhood
    -0.07
    мар
    -0.07
    ron
    -0.06
    POSITIVE LOGITS
    ]['
    0.06
    JK
    0.06
    $$
    0.06
    't
    0.06
    :".$
    0.06
    前に
    0.06
    気
    0.06
    sen
    0.06
    え
    0.06
     chocolates
    0.06
    Act Density 0.034%

    No Known Activations