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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    न्होंने
    -0.08
    -elements
    -0.08
    -being
    -0.08
    .Identifier
    -0.08
     אדער
    -0.08
     мерз
    -0.08
     στοιχεία
    -0.08
    ես
    -0.08
     satisfactory
    -0.07
    -з
    -0.07
    POSITIVE LOGITS
     Normal
    0.08
     milk
    0.08
     Sol
    0.07
     mol
    0.07
     oil
    0.07
     mg
    0.07
     apocalypse
    0.07
    yyy
    0.07
     Comp
    0.07
     mudd
    0.07
    Act Density 0.013%

    No Known Activations