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

    Neuronpedia

    INDEX
    Explanations

    coding syntax related to variable assignments and method invocations in programming

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

    user input start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLI
    -0.54
     فريبيس
    -0.47
     invokingState
    -0.45
    DebuggerNonUser
    -0.45
    IntoConstraints
    -0.44
    pushFollow
    -0.41
    bootstrapcdn
    -0.41
    Chham
    -0.40
     verliert
    -0.38
     Normdatei
    -0.37
    POSITIVE LOGITS
    getIntent
    0.49
    ?}",
    0.49
     getIntent
    0.48
     qu
    0.47
     Dave
    0.43
     Keith
    0.43
    EFIAPI
    0.43
     Heath
    0.43
     Silber
    0.42
    謗
    0.42
    Act Density 0.004%

    No Known Activations