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
    ARB
    -0.07
    enus
    -0.07
    odzi
    -0.07
    sv
    -0.06
    restart
    -0.06
    352
    -0.06
    unload
    -0.06
    'ı
    -0.06
     समझ
    -0.06
    mere
    -0.06
    POSITIVE LOGITS
     horrifying
    0.07
    Miller
    0.07
     funkc
    0.07
     individual
    0.06
     displacement
    0.06
     vh
    0.06
    krét
    0.06
     '/';↵
    0.06
     KW
    0.06
     MYSQL
    0.06
    Act Density 0.003%

    No Known Activations