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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Κ
    -0.07
    casting
    -0.07
     Stunning
    -0.07
     succ
    -0.07
    Fu
    -0.06
     forearm
    -0.06
    的事情
    -0.06
     wc
    -0.06
    CLUDING
    -0.06
     reviews
    -0.06
    POSITIVE LOGITS
    acji
    0.06
    张
    0.06
    _TM
    0.06
    ูต
    0.06
     URLs
    0.06
     appeal
    0.06
     Unlimited
    0.06
     имму
    0.06
     хотел
    0.06
     gew
    0.06
    Act Density 0.024%

    No Known Activations