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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .transactions
    -0.07
     سفر
    -0.07
    ̂
    -0.07
     Empire
    -0.06
    Nil
    -0.06
     nasıl
    -0.06
    cool
    -0.06
     sandwiches
    -0.06
     coraz
    -0.06
    sand
    -0.06
    POSITIVE LOGITS
    /runtime
    0.07
    guard
    0.06
     exact
    0.06
    _WATER
    0.06
    pref
    0.06
    (runtime
    0.06
    \Requests
    0.05
    /%
    0.05
     chute
    0.05
    져
    0.05
    Act Density 0.028%

    No Known Activations