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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tom
    -0.06
     relocated
    -0.06
    commit
    -0.05
    riculum
    -0.05
    ATH
    -0.05
    _errors
    -0.05
    -0.05
    _CON
    -0.05
     boil
    -0.05
     fuzz
    -0.05
    POSITIVE LOGITS
    ...↵↵↵↵
    0.07
    ندگی
    0.07
     своего
    0.07
     การแข
    0.07
    Anchor
    0.07
    brig
    0.07
    ike
    0.07
     　　　　　
    0.07
    lış
    0.07
     организм
    0.06
    Act Density 0.006%

    No Known Activations