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

    Neuronpedia

    INDEX
    Explanations

    Her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    demand
    -0.08
     Pace
    -0.07
     Platz
    -0.07
     větší
    -0.07
     Esp
    -0.06
     Joyce
    -0.06
    	vec
    -0.06
     DATA
    -0.06
     Guang
    -0.06
    	Delete
    -0.06
    POSITIVE LOGITS
     Hers
    0.07
    /red
    0.07
     GER
    0.07
    ERS
    0.06
    (im
    0.06
     Grim
    0.06
    H
    0.06
    /T
    0.06
    μβρίου
    0.06
     Infant
    0.06
    Act Density 0.012%

    No Known Activations