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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     THEY
    -0.06
     Disabilities
    -0.06
    capacity
    -0.06
    -day
    -0.06
    Again
    -0.06
     Personality
    -0.06
    อบ
    -0.06
     eagerly
    -0.06
    ’d
    -0.06
    feito
    -0.06
    POSITIVE LOGITS
    skému
    0.07
     опис
    0.07
    UNDLE
    0.07
     Glam
    0.07
     �
    0.07
    _RT
    0.07
    MaxLength
    0.06
    asan
    0.06
     initi
    0.06
    )[:
    0.06
    Act Density 0.024%

    No Known Activations