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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DB
    -0.07
     xm
    -0.07
     мой
    -0.06
    osing
    -0.06
    IN
    -0.06
     дерева
    -0.06
    .db
    -0.06
    _description
    -0.05
     wins
    -0.05
     являются
    -0.05
    POSITIVE LOGITS
     vody
    0.07
     backpage
    0.07
     Constit
    0.07
    Perhaps
    0.07
     Fully
    0.06
     WideString
    0.06
    기준
    0.06
     ideology
    0.06
     inici
    0.06
    irket
    0.06
    Act Density 0.008%

    No Known Activations