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

    Neuronpedia

    INDEX
    Explanations

    data errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADIO
    -0.07
    Corner
    -0.07
     colle
    -0.07
    /co
    -0.06
     Super
    -0.06
     Cooper
    -0.06
     Blond
    -0.06
    	ctx
    -0.06
     бла
    -0.06
     headphones
    -0.06
    POSITIVE LOGITS
    R
    0.12
     R
    0.12
     RJ
    0.12
    .R
    0.11
     RL
    0.10
     RS
    0.10
     RP
    0.10
     RMS
    0.10
     Ra
    0.10
    r
    0.10
    Act Density 0.418%

    No Known Activations