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

    Neuronpedia

    INDEX
    Explanations

    assess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocha
    -0.06
    APT
    -0.06
     safety
    -0.06
    	current
    -0.06
    acob
    -0.06
    _recv
    -0.06
    аду
    -0.06
     Crate
    -0.06
    isen
    -0.06
     gren
    -0.06
    POSITIVE LOGITS
     estimate
    0.07
    =pd
    0.06
     judged
    0.06
    评
    0.06
     port
    0.06
     mercenaries
    0.06
    _between
    0.06
     Bravo
    0.06
     assessing
    0.06
    PORT
    0.06
    Act Density 0.030%

    No Known Activations