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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (PC
    -0.07
     fanatic
    -0.06
     Least
    -0.06
     self
    -0.06
    isayar
    -0.06
     gerç
    -0.06
     cultivate
    -0.06
    (Self
    -0.06
     Lump
    -0.06
     يكون
    -0.05
    POSITIVE LOGITS
    .sale
    0.07
    .oauth
    0.07
     sidl
    0.07
    ाष
    0.07
    .PUT
    0.06
    Indices
    0.06
     ostat
    0.06
     ellipse
    0.06
    .'_
    0.06
     кас
    0.06
    Act Density 0.003%

    No Known Activations