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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    klady
    -0.07
    _modules
    -0.07
     seams
    -0.07
     Seth
    -0.06
    .z
    -0.06
     narratives
    -0.06
     Brut
    -0.06
     hoops
    -0.06
     bleeding
    -0.06
     Special
    -0.06
    POSITIVE LOGITS
     '{@
    0.07
    บาท
    0.06
    _stamp
    0.06
     مرح
    0.06
     Politico
    0.06
    ecera
    0.06
    <iostream
    0.06
     "(\<
    0.06
     />\
    0.06
    lant
    0.06
    Act Density 0.003%

    No Known Activations