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

    Neuronpedia

    INDEX
    Explanations

    programming/algorithms/research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ja
    -0.06
    (co
    -0.06
    .xz
    -0.06
     ayant
    -0.06
     posted
    -0.05
    Px
    -0.05
     Bin
    -0.05
    GRA
    -0.05
    완
    -0.05
     Cro
    -0.05
    POSITIVE LOGITS
    Mini
    0.07
    irthday
    0.07
    notations
    0.07
    tingham
    0.07
    	mutex
    0.07
     incidence
    0.07
    elfast
    0.07
     toxicity
    0.07
    ozor
    0.06
    니스
    0.06
    Act Density 0.000%

    No Known Activations