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

    Neuronpedia

    INDEX
    Explanations

    suicide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     booklet
    -0.08
    -errors
    -0.07
     Bottle
    -0.07
    .cells
    -0.07
    parallel
    -0.07
    -based
    -0.07
     uveden
    -0.07
    оже
    -0.07
    ontology
    -0.07
    anter
    -0.06
    POSITIVE LOGITS
     Integral
    0.06
    _Tree
    0.06
    етод
    0.06
     scoreboard
    0.06
     сост
    0.06
    outed
    0.06
     익
    0.05
    収
    0.05
                        ↵
    0.05
    ");}↵
    0.05
    Act Density 0.055%

    No Known Activations