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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ElementType
    -0.07
     ambiance
    -0.07
     proto
    -0.06
    Server
    -0.06
     sweat
    -0.06
     Mutex
    -0.06
    .dense
    -0.06
    .:.:.:.:.:.:.:.:
    -0.06
    .cut
    -0.06
     جهان
    -0.06
    POSITIVE LOGITS
     exagger
    0.07
    .Mon
    0.06
    となる
    0.06
    rz
    0.06
    _rewrite
    0.06
     formulate
    0.06
     Publications
    0.06
    _fail
    0.06
    regulated
    0.06
     healthy
    0.06
    Act Density 0.048%

    No Known Activations