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

    Neuronpedia

    INDEX
    Explanations

    connecting concepts or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.56
    Dire
    0.55
    Examples
    0.47
    an
    0.47
    ش
    0.47
    ל
    0.46
    Location
    0.45
    Standard
    0.45
    Khan
    0.44
    DID
    0.43
    POSITIVE LOGITS
    ៧
    0.56
     contradictions
    0.50
     scathing
    0.48
    ៦
    0.48
     :");
    0.46
     répart
    0.46
     fractures
    0.46
     구매
    0.46
    ၆
    0.44
     мнение
    0.44
    Act Density 0.001%

    No Known Activations