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

    Neuronpedia

    INDEX
    Explanations

    outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    26
    -0.08
    ertain
    -0.07
    reation
    -0.07
    yii
    -0.07
    238
    -0.07
    oders
    -0.07
     Aug
    -0.07
    18
    -0.07
    itis
    -0.07
     říj
    -0.07
    POSITIVE LOGITS
     consequences
    0.14
     consequence
    0.10
     CONSEQUENTIAL
    0.08
    sequences
    0.08
     consequently
    0.08
    Cause
    0.07
    наслід
    0.07
    _cons
    0.07
     sonuç
    0.07
     implications
    0.07
    Act Density 0.014%

    No Known Activations