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

    Neuronpedia

    INDEX
    Explanations

    Code and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cooperate
    -0.07
     Baldwin
    -0.07
     coursework
    -0.06
     meetings
    -0.06
     discrete
    -0.06
     Corey
    -0.06
     verbosity
    -0.06
     semanas
    -0.06
     석
    -0.06
     bilim
    -0.06
    POSITIVE LOGITS
    Pref
    0.06
    ाइट
    0.06
    сторія
    0.06
    _mm
    0.06
    atra
    0.06
    اعية
    0.06
    ха
    0.06
     необходим
    0.06
    ып
    0.06
    ]initWithFrame
    0.06
    Act Density 0.058%

    No Known Activations