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

    Neuronpedia

    INDEX
    Explanations

    references to specific items, identifiers, or quantities within a context

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

    z'th term, 2, alerts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.65
     resourceCulture
    -0.61
     snippetHide
    -0.60
    -0.59
    ksessa
    -0.54
     TAMBIÉN
    -0.53
    __":
    -0.53
     Moscú
    -0.53
    AndEndTag
    -0.50
     Geſch
    -0.49
    POSITIVE LOGITS
     Mi
    0.53
     La
    0.52
     Administrativna
    0.49
    WireFormat
    0.47
     "
    0.47
     Tra
    0.46
     Re
    0.46
     tra
    0.46
     Ca
    0.46
    antMatchers
    0.46
    Act Density 0.567%

    No Known Activations