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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific measurements and experiments

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

    pump/probe/target/training signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.49
    tvguidetime
    -0.44
    MethodManager
    -0.42
     route
    -0.40
    Route
    -0.38
     Route
    -0.38
    Hh
    -0.38
     cn
    -0.38
     Numerade
    -0.37
     sem
    -0.36
    POSITIVE LOGITS
    berdayakan
    0.58
    ajur
    0.47
     zwey
    0.46
    calientes
    0.46
     <<<<<<<<<<<<<<
    0.46
     lizenzfreie
    0.45
     Putih
    0.45
     onBind
    0.45
     purpoſe
    0.44
    انجليز
    0.44
    Act Density 0.445%

    No Known Activations