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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atrice
    -0.07
     السن
    -0.07
    흠
    -0.07
    凰
    -0.07
    <t
    -0.06
    fft
    -0.06
    身
    -0.06
    𬤇
    -0.06
    ставлен
    -0.06
     Văn
    -0.06
    POSITIVE LOGITS
    '],$
    0.07
     nost
    0.07
    ☄
    0.07
    ប
    0.07
    '.$
    0.07
     nadzie
    0.07
     "&#
    0.07
    مساعدة
    0.07
     wurden
    0.06
    Neo
    0.06
    Act Density 0.001%

    No Known Activations