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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvement and progress in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    progressing or continuing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financiamiento
    -0.42
     pesada
    -0.37
    ]=-
    -0.36
     يتيمه
    -0.36
    Recruit
    -0.36
     fundido
    -0.36
     ilegal
    -0.35
    AutoScaleMode
    -0.35
     protoimpl
    -0.35
     financement
    -0.35
    POSITIVE LOGITS
    :✨
    0.47
    exitRule
    0.44
    WireFormatLite
    0.44
    RenderAtEndOf
    0.42
     Himo
    0.41
    省市镇
    0.41
    ⟬
    0.40
    issauga
    0.40
    trab
    0.39
    ResponseWriter
    0.39
    Act Density 0.050%

    No Known Activations