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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _attack
    -0.07
    itet
    -0.07
    instanc
    -0.07
    getStatus
    -0.07
    �
    -0.07
    unifu
    -0.07
    olec
    -0.06
     соврем
    -0.06
    absolute
    -0.06
     Mädchen
    -0.06
    POSITIVE LOGITS
    Or
    0.12
     Or
    0.12
    .Or
    0.11
     OR
    0.09
    -or
    0.08
    /or
    0.07
    Ur
    0.07
     Ur
    0.07
    _or
    0.07
     par
    0.07
    Act Density 0.010%

    No Known Activations