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

    Neuronpedia

    INDEX
    Explanations

    Dirty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towing
    -0.06
    Overview
    -0.06
    _PLAY
    -0.06
     legs
    -0.06
    _encode
    -0.06
     cult
    -0.06
    -search
    -0.06
     joe
    -0.06
    girls
    -0.06
    Za
    -0.06
    POSITIVE LOGITS
     nedok
    0.07
    /s
    0.07
    ?#
    0.07
    ={(
    0.07
    ]}"
    0.06
    کش
    0.06
    َد
    0.06
    _COLLECTION
    0.06
    ibilidade
    0.06
    (remote
    0.06
    Act Density 0.005%

    No Known Activations