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

    Neuronpedia

    INDEX
    Explanations

    off on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    安慰
    0.42
     क्रिप्टोकर
    0.40
     Pfaff
    0.39
    ught
    0.39
     rags
    0.39
     Primera
    0.38
     Vienna
    0.38
    ircraft
    0.38
     Tweed
    0.38
     anecdotal
    0.38
    POSITIVE LOGITS
    选
    0.39
     kullanılır
    0.38
     સ્વ
    0.37
    attamente
    0.37
     राज्यों
    0.36
     chọn
    0.35
     Chọn
    0.35
    Enlaces
    0.35
     jeweils
    0.35
     kullanıl
    0.34
    Act Density 0.000%

    No Known Activations