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

    Neuronpedia

    INDEX
    Explanations

    Legal/business contracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itin
    -0.07
    constraint
    -0.06
     Garage
    -0.06
     будів
    -0.06
    mse
    -0.06
    LOOR
    -0.06
     biomass
    -0.06
     docking
    -0.06
    RuleContext
    -0.06
    BMI
    -0.06
    POSITIVE LOGITS
    PT
    0.07
     juste
    0.07
    .toastr
    0.07
    �
    0.07
    game
    0.07
    )"
    0.06
     Männer
    0.06
    ¯¯¯¯
    0.06
    _INITIALIZ
    0.06
     Telegraph
    0.06
    Act Density 0.033%

    No Known Activations