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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Visited
    -0.07
    �
    -0.07
    茄子
    -0.07
    <fieldset
    -0.07
     putt
    -0.06
     pits
    -0.06
    iosis
    -0.06
    יס
    -0.06
    _CONTAINER
    -0.06
    ᾰ
    -0.06
    POSITIVE LOGITS
     kısa
    0.07
     Attack
    0.07
    问问
    0.07
     Kn
    0.06
    Sh
    0.06
     employee
    0.06
     Sight
    0.06
     setw
    0.06
    ___↵↵
    0.06
     узна
    0.06
    Act Density 0.001%

    No Known Activations