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

    Neuronpedia

    INDEX
    Explanations

    Ryan, Rex, Peru, Puancare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     K
    0.45
     ک
    0.45
     eng
    0.44
    Eng
    0.42
     Eng
    0.41
     Sa
    0.41
    Sa
    0.40
     الأد
    0.36
     ਸਾ
    0.36
    バ
    0.35
    POSITIVE LOGITS
     Rey
    0.44
    bones
    0.42
     rex
    0.40
     Rex
    0.40
    Reynolds
    0.39
    Rey
    0.38
    𝔼
    0.38
     buoni
    0.38
     pearl
    0.37
    Pearl
    0.36
    Act Density 0.010%

    No Known Activations