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

    Neuronpedia

    INDEX
    Explanations

    parameters and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ઢી
    0.38
    zo
    0.38
    ης
    0.38
     AAS
    0.38
    IGO
    0.37
    =
    0.37
    APA
    0.37
     Alice
    0.37
     preserved
    0.36
    zza
    0.36
    POSITIVE LOGITS
     font
    0.42
    font
    0.39
     ഞാന്‍
    0.39
    elab
    0.38
    Font
    0.37
     ужа
    0.37
    数の
    0.37
    stilling
    0.37
    교육
    0.36
     Sick
    0.36
    Act Density 0.001%

    No Known Activations