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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     substances
    -0.06
     falsely
    -0.06
    'na
    -0.06
     find
    -0.06
    ifik
    -0.06
     taps
    -0.06
     prostředí
    -0.06
     reactions
    -0.06
     actions
    -0.06
     sok
    -0.06
    POSITIVE LOGITS
     Homework
    0.07
    rido
    0.07
    mine
    0.07
     reloc
    0.07
     postav
    0.07
    itesi
    0.06
    │
    0.06
    /respond
    0.06
    ριά
    0.06
     buoy
    0.06
    Act Density 0.045%

    No Known Activations