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

    Neuronpedia

    INDEX
    Explanations

    Security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PIPE
    -0.06
    _nh
    -0.06
    _devices
    -0.06
     großen
    -0.06
     studi
    -0.06
     rearr
    -0.06
     мови
    -0.06
     schöne
    -0.06
    _apps
    -0.06
    .regex
    -0.06
    POSITIVE LOGITS
    зы
    0.07
     conveyor
    0.07
     permissible
    0.07
    redicate
    0.07
     conviction
    0.07
    utenant
    0.06
    ávají
    0.06
     invokes
    0.06
     security
    0.06
    (eval
    0.06
    Act Density 0.003%

    No Known Activations