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

    Neuronpedia

    INDEX
    Explanations

    instances of missing or unsuccessful actions

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

    miss or out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.60
     feroit
    -0.45
     colo
    -0.44
    ፩
    -0.43
    SequentialGroup
    -0.43
     surla
    -0.42
    providedIn
    -0.40
     Савезне
    -0.40
    ipient
    -0.39
    StateManager
    -0.38
    POSITIVE LOGITS
     wasting
    0.44
     disappointed
    0.43
     disappoint
    0.42
    esez
    0.40
    arraycopy
    0.40
     unsuccessfully
    0.40
     disappointing
    0.39
    👎
    0.38
    astéroïdes
    0.38
    wegg
    0.38
    Act Density 0.010%

    No Known Activations