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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    茎
    -0.08
    ಡ
    -0.08
     loyal
    -0.07
    𝓽
    -0.07
    𝚃
    -0.07
     Araştırma
    -0.07
    Ф
    -0.07
     histo
    -0.07
    และ
    -0.07
    ⌚
    -0.07
    POSITIVE LOGITS
    antis
    0.07
     BLACK
    0.07
     scal
    0.07
     Anglic
    0.07
    無し�
    0.06
     slump
    0.06
     Float
    0.06
     demonstr
    0.06
    ropic
    0.06
     reinst
    0.06
    Act Density 0.000%

    No Known Activations