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

    Neuronpedia

    INDEX
    Explanations

    clar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    0.61
    愔
    0.54
    棪
    0.53
    "/"
    0.51
     effett
    0.51
     Фурга
    0.50
    "-"
    0.50
     মত
    0.49
    "="
    0.49
    arbeitung
    0.48
    POSITIVE LOGITS
    ל
    0.69
    ap
    0.65
    !]
    0.60
    ین
    0.59
    ید
    0.58
    UT
    0.57
    J
    0.55
    excluding
    0.54
    ase
    0.54
    Z
    0.52
    Act Density 0.020%

    No Known Activations