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

    Neuronpedia

    INDEX
    Explanations

    console

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الخلق
    0.36
    MessageType
    0.36
    AnimationStyle
    0.36
    excel
    0.35
    gimento
    0.35
     '\\
    0.35
    ති
    0.35
    pert
    0.35
    dav
    0.35
    hx
    0.34
    POSITIVE LOGITS
     Goodwin
    0.43
    conditionals
    0.43
     उपायों
    0.41
     टेंपरे
    0.41
     conditionals
    0.41
     Volt
    0.41
    าลัย
    0.41
     clauses
    0.40
     Pause
    0.40
     Laplacian
    0.40
    Act Density 0.001%

    No Known Activations