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

    Neuronpedia

    INDEX
    Explanations

    Stepping on something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <b
    -0.07
     dikke
    -0.07
    creat
    -0.07
     campos
    -0.07
     otevř
    -0.07
    пня
    -0.07
    Offer
    -0.06
    Hashtable
    -0.06
     Improve
    -0.06
     πάνω
    -0.06
    POSITIVE LOGITS
    　　　　
    0.06
    (created
    0.06
    pressions
    0.06
     bash
    0.06
     primes
    0.06
    ([&
    0.06
     [...
    0.06
    LIGHT
    0.05
     роботу
    0.05
    #'
    0.05
    Act Density 0.062%

    No Known Activations