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

    Neuronpedia

    INDEX
    Explanations

    financial performance metrics related to movies

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

    to make user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لينكات
    -0.41
    gląd
    -0.32
    WithMany
    -0.31
     riferimento
    -0.27
     palha
    -0.27
    TextEditing
    -0.26
     diken
    -0.26
     bezeichnen
    -0.26
     prática
    -0.24
     voyons
    -0.24
    POSITIVE LOGITS
     cinemas
    0.72
    ConstraintMaker
    0.62
     surla
    0.62
     blockbuster
    0.61
     theaters
    0.58
    нгред
    0.57
    (!__
    0.57
    InjectAttribute
    0.55
     gynhyrchwyd
    0.55
    prechpartner
    0.55
    Act Density 0.014%

    No Known Activations