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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    출
    -0.07
    네
    -0.07
    -O
    -0.06
     ترجم
    -0.06
     True
    -0.06
    ışman
    -0.06
    ">↵
    -0.06
     قال
    -0.06
     expos
    -0.06
    jwt
    -0.06
    POSITIVE LOGITS
    apped
    0.07
     erupt
    0.06
    (machine
    0.06
    patibility
    0.06
    /object
    0.06
    ROOT
    0.06
     volver
    0.06
    nung
    0.06
    uctose
    0.06
     skoro
    0.06
    Act Density 0.028%

    No Known Activations