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

    Neuronpedia

    INDEX
    Explanations

    references to political scandals, figures, and investigations.

    oai_token-act-pair · gemini-2.0-flash

    Trump

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+
    -0.66
    первых
    -0.56
    vstack
    -0.54
    bows
    -0.52
    sune
    -0.49
     onAnimation
    -0.49
    DebuggerNonUser
    -0.49
    UpInside
    -0.49
    MetaObject
    -0.48
    GMT
    -0.48
    POSITIVE LOGITS
     nakalista
    0.57
     Walkover
    0.55
    kuuta
    0.53
    itor
    0.51
    erover
    0.49
    uito
    0.49
     rhestr
    0.48
    ernes
    0.47
    ITOR
    0.46
     buta
    0.46
    Act Density 0.978%

    No Known Activations