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

    Neuronpedia

    INDEX
    Explanations

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boil
    -0.07
    ADV
    -0.06
     سور
    -0.06
    Lit
    -0.06
    _outer
    -0.06
    .connection
    -0.06
    ne
    -0.06
     ])
    -0.06
     hấp
    -0.06
     derivative
    -0.06
    POSITIVE LOGITS
     hton
    0.07
     星
    0.07
    ٫
    0.07
    essim
    0.07
    ’m
    0.06
    Architecture
    0.06
    imestone
    0.06
    essions
    0.06
    rl
    0.06
    .twitch
    0.06
    Act Density 0.003%

    No Known Activations