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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" and variations of learning or discovering something

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

    learning or discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁴
    -0.48
    vis
    -0.44
     descriptive
    -0.40
    MinWidth
    -0.39
    Initial
    -0.39
     dorada
    -0.38
     visions
    -0.38
    okok
    -0.38
    utama
    -0.37
    Directions
    -0.37
    POSITIVE LOGITS
    TargetException
    0.61
    principalColumn
    0.61
    providedIn
    0.58
     <=",
    0.57
    InSection
    0.55
    principalTable
    0.54
    ScopeManager
    0.54
    AlterField
    0.53
    stateMutability
    0.53
    EnableWeb
    0.51
    Act Density 0.050%

    No Known Activations