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

    Neuronpedia

    INDEX
    Explanations

    Starting new actions/plans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _av
    -0.06
     晴
    -0.06
     �
    -0.06
     мест
    -0.06
    .CopyTo
    -0.06
     fug
    -0.06
     vat
    -0.06
    芙
    -0.06
    相
    -0.06
    plitude
    -0.06
    POSITIVE LOGITS
    Negative
    0.07
    !↵↵
    0.06
    }
↵
↵
    0.06
    "][$
    0.06
     parler
    0.06
    responsive
    0.06
    ..↵↵
    0.06
    ocrisy
    0.06
     Learned
    0.06
     Buddhist
    0.06
    Act Density 0.028%

    No Known Activations