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

    Neuronpedia

    INDEX
    Explanations

    probability calculations with letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crisis
    -0.07
     compet
    -0.07
     urgent
    -0.06
     fug
    -0.06
     EXISTS
    -0.06
    Legendary
    -0.06
     mouth
    -0.06
     chicks
    -0.06
     deception
    -0.06
    422
    -0.06
    POSITIVE LOGITS
    атора
    0.07
    ekte
    0.07
    anked
    0.06
    -----
    0.06
    .Optional
    0.06
    ($.
    0.06
    �
    0.06
    541
    0.06
     دست
    0.06
     repealed
    0.06
    Act Density 0.005%

    No Known Activations