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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twins
    -0.07
    iami
    -0.07
    -than
    -0.07
    ","");↵
    -0.07
    	bt
    -0.07
    /out
    -0.06
     businessman
    -0.06
     prez
    -0.06
     onFocus
    -0.06
     shameful
    -0.06
    POSITIVE LOGITS
    icip
    0.07
    Pref
    0.06
    ева
    0.06
    Elim
    0.06
    _allocated
    0.06
     CLIIIK
    0.06
     incre
    0.06
    ,it
    0.06
    َي
    0.06
     обл
    0.06
    Act Density 0.083%

    No Known Activations