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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绺
    -0.06
    allon
    -0.06
    irected
    -0.06
     stap
    -0.06
     flowed
    -0.06
    쳥
    -0.06
    哞
    -0.06
    ניתוח
    -0.06
    ๛
    -0.06
     TreeMap
    -0.06
    POSITIVE LOGITS
     nth
    0.08
     burden
    0.07
    /she
    0.06
    ינת
    0.06
    诸
    0.06
    俜
    0.06
     Semester
    0.06
    �
    0.06
    refs
    0.06
    _RS
    0.06
    Act Density 0.001%

    No Known Activations