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

    Neuronpedia

    INDEX
    Explanations

    exotic things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Co
    -1.04
    exotic
    -0.80
     exotic
    -0.77
     powder
    -0.76
     tartalomajánló
    -0.76
    Co
    -0.75
    EDEFAULT
    -0.74
     Мексичка
    -0.73
    ]-'
    -0.72
    powder
    -0.69
    POSITIVE LOGITS
    a
    0.54
    e
    0.54
     الحره
    0.52
    per
    0.49
    lo
    0.48
    loc
    0.48
    er
    0.46
    dif
    0.46
    la
    0.43
    ded
    0.42
    Act Density 0.384%

    No Known Activations