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

    Neuronpedia

    INDEX
    Explanations

    magnetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aligned
    -0.07
    Invariant
    -0.07
    毒
    -0.07
    усти
    -0.07
    ogen
    -0.06
    ัวอย
    -0.06
     variants
    -0.06
    _GU
    -0.06
    /loader
    -0.06
     Ar
    -0.06
    POSITIVE LOGITS
     BigInt
    0.07
    -pages
    0.06
    軟
    0.06
    pesan
    0.06
    []=
    0.06
    °}
    0.06
    197
    0.06
    Spark
    0.06
    Mate
    0.06
    ');?></
    0.06
    Act Density 0.001%

    No Known Activations