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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "first" and related terms indicating initial steps or beginnings

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

    first followed by an initial noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sendRedirect
    -0.41
     tarko
    -0.38
     ocupado
    -0.38
     akun
    -0.35
     hablado
    -0.35
     révé
    -0.35
     huom
    -0.34
     mierda
    -0.33
    äuser
    -0.33
    quele
    -0.32
    POSITIVE LOGITS
     surla
    0.60
     ModelExpression
    0.59
    Tango
    0.55
    ChildScrollView
    0.51
     NgModule
    0.50
    GLP
    0.50
    TagMode
    0.49
     Cæsar
    0.47
     allAfrica
    0.47
    ſelf
    0.47
    Act Density 0.041%

    No Known Activations