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

    Neuronpedia

    INDEX
    Explanations

    resist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (jLabel
    -0.07
     commonplace
    -0.07
     Merkez
    -0.06
    -0.06
    approx
    -0.06
    firefox
    -0.06
    >Password
    -0.06
     profiler
    -0.06
     marine
    -0.06
     cleared
    -0.06
    POSITIVE LOGITS
     resisting
    0.08
     resisted
    0.08
     resist
    0.07
     irresistible
    0.07
    mpp
    0.07
    hosts
    0.07
    َس
    0.06
    _UINT
    0.06
    (csv
    0.06
     oppression
    0.06
    Act Density 0.007%

    No Known Activations