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

    Neuronpedia

    INDEX
    Explanations

    California

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indi
    -0.07
    (char
    -0.07
    	ext
    -0.07
    _store
    -0.07
     storia
    -0.07
     lex
    -0.07
    rf
    -0.06
    (ns
    -0.06
    rapper
    -0.06
    ovies
    -0.06
    POSITIVE LOGITS
    บางคน
    0.07
    ลงไป
    0.07
     الكبر
    0.07
    acakt
    0.07
    엃
    0.06
    أخ
    0.06
     Pew
    0.06
    纷纷
    0.06
     possibility
    0.06
     mechanism
    0.06
    Act Density 0.008%

    No Known Activations