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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getZ
    -0.08
    activity
    -0.07
    というのは
    -0.07
    ampionship
    -0.07
     ix
    -0.06
     specifications
    -0.06
     cour
    -0.06
     bundle
    -0.06
    しましょう
    -0.06
    绍兴
    -0.06
    POSITIVE LOGITS
    שג
    0.08
    BOOLE
    0.07
    PLOY
    0.07
     entra
    0.07
    .FONT
    0.07
    Jwt
    0.07
    :def
    0.07
     adequate
    0.07
    .Design
    0.06
    (COLOR
    0.06
    Act Density 0.014%

    No Known Activations