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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     výrob
    -0.08
     call
    -0.07
     mood
    -0.07
    Voice
    -0.07
    _space
    -0.07
     sunlight
    -0.07
     fim
    -0.06
    MEMORY
    -0.06
     redhead
    -0.06
     dagen
    -0.06
    POSITIVE LOGITS
    }");↵
    0.07
     الفر
    0.07
    .Inst
    0.06
     вок
    0.06
     Athens
    0.06
    ังส
    0.06
    ΡΓ
    0.06
    ')}</
    0.06
    |(↵
    0.06
     semiclass
    0.06
    Act Density 0.001%

    No Known Activations