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
    forcer
    -0.07
    agens
    -0.07
    rir
    -0.06
     Uk
    -0.06
     learner
    -0.06
     Likely
    -0.06
     EEPROM
    -0.06
     cán
    -0.06
     Summers
    -0.06
     ALWAYS
    -0.06
    POSITIVE LOGITS
     Pilot
    0.06
    .interpolate
    0.06
    _gradient
    0.06
    玄
    0.06
     Nik
    0.06
    (fid
    0.06
     NOI
    0.06
    ()?
    0.06
    џџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџ
    0.06
    (|
    0.06
    Act Density 0.022%

    No Known Activations