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

    Neuronpedia

    INDEX
    Explanations

    ulating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rev
    -0.06
    ρή
    -0.06
    mayan
    -0.06
    .exp
    -0.06
     Jeho
    -0.06
     owes
    -0.06
     dog
    -0.06
    	args
    -0.06
    _no
    -0.06
     sovereign
    -0.06
    POSITIVE LOGITS
     Jelly
    0.07
    .BL
    0.07
     insulated
    0.07
     insulation
    0.07
     vitam
    0.07
     ilan
    0.07
     університет
    0.06
    ICTURE
    0.06
    ,ev
    0.06
    training
    0.06
    Act Density 0.005%

    No Known Activations