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

    Neuronpedia

    INDEX
    Explanations

    memory addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ℂ
    -0.07
    られて
    -0.07
     maxSize
    -0.07
     frame
    -0.07
     désorm
    -0.07
    endereco
    -0.06
    胬
    -0.06
    .getSeconds
    -0.06
     outFile
    -0.06
    ᾧ
    -0.06
    POSITIVE LOGITS
    gypt
    0.07
    .ml
    0.07
     trains
    0.07
    baum
    0.07
    日渐
    0.07
    Runs
    0.07
    Quick
    0.07
    cant
    0.07
    _ready
    0.07
     suicides
    0.06
    Act Density 0.002%

    No Known Activations