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

    Neuronpedia

    INDEX
    Explanations

    verbs related to capability or action

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

    what can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.53
    φη
    -0.36
    ritto
    -0.36
    áját
    -0.35
     Defining
    -0.35
     defining
    -0.34
     confezione
    -0.33
    ámb
    -0.33
     announcing
    -0.32
     ORDIN
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.63
    TestingModule
    0.59
    SerializedSize
    0.57
    tanooga
    0.57
    InputBorder
    0.55
    ThroughAttribute
    0.52
    windowFixed
    0.49
    لينكات
    0.48
    ⤹
    0.47
     canst
    0.46
    Act Density 0.007%

    No Known Activations