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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     통해
    -0.06
     AudioSource
    -0.06
    Command
    -0.06
    Reverse
    -0.06
    ouple
    -0.06
    적으로
    -0.06
     incarnation
    -0.06
    ividual
    -0.06
     Fuk
    -0.06
     同
    -0.06
    POSITIVE LOGITS
     essen
    0.07
    جمة
    0.07
     Martin
    0.06
     CT
    0.06
    	sprite
    0.06
     esse
    0.06
     البته
    0.06
    /token
    0.06
     μέχρι
    0.06
    .graph
    0.06
    Act Density 0.009%

    No Known Activations