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

    Neuronpedia

    INDEX
    Explanations

    Dwight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ejemplo
    -0.07
     симв
    -0.06
     trabal
    -0.06
    完成
    -0.06
    ="[
    -0.06
    енной
    -0.06
    屬
    -0.06
    ¾
    -0.06
    ksen
    -0.06
    صال
    -0.06
    POSITIVE LOGITS
    pread
    0.06
     fauna
    0.06
    	y
    0.06
    _CONST
    0.06
    Kitchen
    0.06
    งเศส
    0.06
    ्रण
    0.06
    звичай
    0.06
    _mouse
    0.06
     playbook
    0.06
    Act Density 0.006%

    No Known Activations