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

    Neuronpedia

    INDEX
    Explanations

    Placeholders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UpEdit
    -0.07
     Armen
    -0.07
    Exception
    -0.07
     ")↵↵
    -0.06
    ーの
    -0.06
    .c
    -0.06
     ----------------------------------------------------------------
    -0.06
     naked
    -0.06
     >&
    -0.06
    ="\
    -0.06
    POSITIVE LOGITS
    สำเร
    0.07
    Escort
    0.06
     일정
    0.06
     driv
    0.06
    키
    0.06
    
    0.06
    �
    0.06
    ears
    0.06
    ivr
    0.06
    рост
    0.06
    Act Density 0.042%

    No Known Activations