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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding and recognition of emotions or relationships

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

    fellow understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.54
    marily
    -0.52
    orin
    -0.44
    onOptions
    -0.44
    entist
    -0.44
    tonsoft
    -0.43
    ophon
    -0.43
    TintMode
    -0.43
     Chairs
    -0.43
    phenol
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.55
    /*
    0.42
    /**
    0.41
    Geplaatst
    0.41
    
    0.40
    /***/
    0.38
    Życiorys
    0.36
     labios
    0.35
    ScopeManager
    0.34
    новништво
    0.34
    Act Density 0.019%

    No Known Activations