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

    Neuronpedia

    INDEX
    Explanations

    references to personal experience and professional backgrounds

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

    years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (!__
    -0.47
     <=",
    -0.41
     ProtoMessage
    -0.38
     <<<<<<<<<<<<<<
    -0.38
    ServletRequest
    -0.37
    POP
    -0.37
    ModelAdmin
    -0.37
    あたり
    -0.36
     fo
    -0.36
    action
    -0.36
    POSITIVE LOGITS
     expérimentés
    0.77
     experience
    0.75
     expertise
    0.72
     experto
    0.67
     experienced
    0.66
     EXPERIENCE
    0.65
    EXPERIENCE
    0.63
    experience
    0.63
     expert
    0.62
     experiencia
    0.61
    Act Density 0.009%

    No Known Activations