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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manoe
    -0.07
     Matching
    -0.06
    ording
    -0.06
    rier
    -0.06
     kom
    -0.06
    ö
    -0.06
    erken
    -0.06
     Stam
    -0.06
    ペ
    -0.06
    ival
    -0.06
    POSITIVE LOGITS
    -react
    0.07
     orally
    0.07
    ):(
    0.06
     wordpress
    0.06
     obdob
    0.06
    813
    0.06
     discharge
    0.06
    _COMMENT
    0.06
     perpetual
    0.06
    .“
    0.06
    Act Density 0.001%

    No Known Activations