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

    Neuronpedia

    INDEX
    Explanations

    fitness and toning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otel
    -0.07
     hosp
    -0.07
    lique
    -0.06
    _whitespace
    -0.06
    、“
    -0.06
     пло
    -0.06
    ウ
    -0.06
    Selective
    -0.06
     crosses
    -0.06
    罪
    -0.06
    POSITIVE LOGITS
    abilia
    0.06
     cầm
    0.06
     recursive
    0.06
    álním
    0.06
     Amerikan
    0.06
    想
    0.06
    clusion
    0.06
    redict
    0.06
    (Buffer
    0.06
     생각
    0.06
    Act Density 0.043%

    No Known Activations