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

    Neuronpedia

    INDEX
    Explanations

    _AUX

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .foo
    -0.07
    лас
    -0.06
    _sensor
    -0.06
    fter
    -0.06
    .is
    -0.06
    ese
    -0.06
    Remote
    -0.06
    委
    -0.06
    .Se
    -0.06
    ания
    -0.06
    POSITIVE LOGITS
     Eisenhower
    0.18
    hower
    0.11
    _AUX
    0.10
     Paso
    0.10
     Unsure
    0.07
    Registro
    0.07
    <Color
    0.07
     LinkedList
    0.06
    }")]↵
    0.06
    BOSE
    0.06
    Act Density 0.002%

    No Known Activations