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

    Neuronpedia

    INDEX
    Explanations

    standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sexo
    -0.06
    (ix
    -0.06
     Kub
    -0.06
     llegar
    -0.06
    imet
    -0.06
     offs
    -0.06
    .nextInt
    -0.06
     мона
    -0.06
    рави
    -0.06
     Nicaragua
    -0.05
    POSITIVE LOGITS
     parses
    0.08
     standards
    0.08
    Narrated
    0.08
    ชาว
    0.07
     '.
    0.07
     همچ
    0.07
    '.
    0.07
    Dll
    0.07
    directory
    0.07
     prayers
    0.06
    Act Density 0.006%

    No Known Activations