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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aston
    -0.07
    ının
    -0.07
     Carbon
    -0.07
     Rue
    -0.06
     가정
    -0.06
    琴
    -0.06
     Fight
    -0.06
     slap
    -0.06
    _signup
    -0.06
     carbon
    -0.06
    POSITIVE LOGITS
     Japon
    0.06
    oubtedly
    0.06
     yapılması
    0.06
     useCallback
    0.06
     {}).
    0.06
     Homo
    0.06
    .panelControl
    0.06
    owner
    0.06
    ậc
    0.06
    ocity
    0.06
    Act Density 0.645%

    No Known Activations