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

    Neuronpedia

    INDEX
    Explanations

    math forum questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jeho
    -0.07
     degree
    -0.06
     Grad
    -0.06
    (EXPR
    -0.06
     artillery
    -0.06
     Hamp
    -0.06
     pundits
    -0.06
    (variable
    -0.06
    прав
    -0.06
    phinx
    -0.06
    POSITIVE LOGITS
    annels
    0.07
     活
    0.06
    _exchange
    0.06
    ùy
    0.06
     //================================================================
    0.06
     бар
    0.06
    纳
    0.06
    LING
    0.06
     كار
    0.06
     reak
    0.06
    Act Density 0.005%

    No Known Activations