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

    Neuronpedia

    INDEX
    Explanations

    Java method declarations and related programming constructs

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

    Code snippets using "Object" or "object"

    np_acts-logits-general · gemini-2.0-flash

    object or variable access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ause
    -0.48
    duga
    -0.47
    maven
    -0.47
    ITECH
    -0.46
    WireFormatLite
    -0.46
    lew
    -0.46
    ásban
    -0.46
    సు
    -0.45
    max
    -0.45
    ➟
    -0.45
    POSITIVE LOGITS
    getValueAt
    0.70
    JspWriter
    0.68
     مشين
    0.68
     localObject
    0.67
    andidaten
    0.63
     objects
    0.60
    écnicas
    0.60
     object
    0.58
     Object
    0.58
    kmal
    0.57
    Act Density 0.182%

    No Known Activations