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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     from
    -0.07
    ntax
    -0.07
    _history
    -0.07
     Conway
    -0.06
     rehabilit
    -0.06
    警
    -0.06
     regular
    -0.06
     pls
    -0.06
    ExecutionContext
    -0.06
    wc
    -0.06
    POSITIVE LOGITS
    越
    0.06
    阪
    0.06
     Ole
    0.06
    čila
    0.06
    يدة
    0.06
     Pitch
    0.06
    之一
    0.06
    Secret
    0.06
    _perm
    0.06
     Naturally
    0.06
    Act Density 0.004%

    No Known Activations