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

    Neuronpedia

    INDEX
    Explanations

    terms related to contractual obligations and performance metrics

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

    following a process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.43
     geworden
    -0.43
    🔕
    -0.35
    declare
    -0.33
    textLabel
    -0.32
    iner
    -0.32
    BagLayout
    -0.32
    ulls
    -0.31
    BagConstraints
    -0.31
    uni
    -0.31
    POSITIVE LOGITS
    UrlResolution
    0.60
    DockStyle
    0.58
    évaluateur
    0.55
    PostInfinity
    0.52
     onAnimation
    0.51
     kasarigan
    0.50
    httphttps
    0.49
     kaarangay
    0.49
    aarrggbb
    0.49
     <<<<<<<<<<<<<<
    0.47
    Act Density 0.151%

    No Known Activations