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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الموقع
    -0.07
     dx
    -0.07
     ת
    -0.07
    omial
    -0.07
     Fr
    -0.07
    pres
    -0.06
     naz
    -0.06
     вы
    -0.06
     Bust
    -0.06
    	dispatch
    -0.06
    POSITIVE LOGITS
    opathic
    0.07
     CONSTANTS
    0.07
    爱上
    0.07
    忉
    0.07
     płyn
    0.06
     Emanuel
    0.06
     Connie
    0.06
    碃
    0.06
    -boot
    0.06
    _schema
    0.06
    Act Density 0.000%

    No Known Activations