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

    Neuronpedia

    INDEX
    Explanations

    FILE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edith
    -0.07
    izin
    -0.07
     potato
    -0.07
     traged
    -0.07
    aycast
    -0.07
    ुत
    -0.06
    (training
    -0.06
    (command
    -0.06
    unk
    -0.06
    .setSelected
    -0.06
    POSITIVE LOGITS
     midst
    0.07
     misc
    0.07
     remodel
    0.06
    arlar
    0.06
     ::↵
    0.06
    WG
    0.06
    مر
    0.06
    终
    0.06
    _DEFINITION
    0.06
    hf
    0.06
    Act Density 0.001%

    No Known Activations