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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uddenly
    -0.08
    -blue
    -0.07
     sprung
    -0.07
    .Models
    -0.07
     stealth
    -0.07
    =response
    -0.07
    =message
    -0.06
     disillusion
    -0.06
    -expand
    -0.06
    艎
    -0.06
    POSITIVE LOGITS
    ime
    0.08
     engaging
    0.07
     erre
    0.07
     ⟨
    0.07
    imed
    0.07
     Chavez
    0.07
     sqrt
    0.06
     "";↵↵
    0.06
     Median
    0.06
     são
    0.06
    Act Density 0.004%

    No Known Activations