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

    Neuronpedia

    INDEX
    Explanations

    certifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fuck
    -0.07
    押
    -0.07
    anzi
    -0.07
    PLIER
    -0.06
     Advocate
    -0.06
    чно
    -0.06
    rig
    -0.06
    Fuck
    -0.06
    >>>>
    -0.06
     Peggy
    -0.06
    POSITIVE LOGITS
    _HEADER
    0.08
    _CHARSET
    0.07
    [input
    0.07
    τής
    0.07
     earthly
    0.07
    PreparedStatement
    0.06
     ABOUT
    0.06
    HQ
    0.06
     unreachable
    0.06
     mongodb
    0.06
    Act Density 0.014%

    No Known Activations