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

    Neuronpedia

    INDEX
    Explanations

    levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	M
    -0.07
    _ENSURE
    -0.06
    cluding
    -0.06
    .KeyPress
    -0.06
    716
    -0.06
    646
    -0.06
    .what
    -0.06
    ynes
    -0.06
    .age
    -0.06
     grabs
    -0.06
    POSITIVE LOGITS
     Vanilla
    0.07
     strategies
    0.07
     발표
    0.07
     hafif
    0.06
     vå
    0.06
    าชน
    0.06
     분
    0.06
    _doc
    0.06
     قم
    0.06
    λοι
    0.06
    Act Density 0.032%

    No Known Activations