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

    Neuronpedia

    INDEX
    Explanations

    leave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _prot
    -0.07
     propagation
    -0.07
    -making
    -0.07
    Consider
    -0.06
    یم
    -0.06
     �
    -0.06
     Stitch
    -0.06
    ToAdd
    -0.06
    เจ
    -0.06
    Employ
    -0.06
    POSITIVE LOGITS
     leave
    0.08
     journeys
    0.07
     Leave
    0.07
     leaving
    0.07
     commenter
    0.06
     signs
    0.06
    ef
    0.06
     pratic
    0.06
     가족
    0.06
     Santos
    0.06
    Act Density 0.014%

    No Known Activations