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

    Neuronpedia

    INDEX
    Explanations

    Industrial spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Backup
    -0.07
    _probe
    -0.07
     chip
    -0.06
     Waste
    -0.06
    เ�
    -0.06
     Testing
    -0.06
    weight
    -0.06
     borough
    -0.06
     suicide
    -0.06
    ’est
    -0.06
    POSITIVE LOGITS
     그는
    0.07
     trưng
    0.07
     studs
    0.07
     klin
    0.06
     Kap
    0.06
    .<
    0.06
    _embed
    0.06
     kata
    0.06
    튜
    0.06
    .'
    0.06
    Act Density 0.051%

    No Known Activations