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
     üret
    -0.07
    üml
    -0.07
     Maple
    -0.06
     transcript
    -0.06
    -Regular
    -0.06
     zach
    -0.06
    emb
    -0.06
    _activation
    -0.06
    oward
    -0.06
     दब
    -0.06
    POSITIVE LOGITS
    cantidad
    0.07
    ило
    0.07
    je
    0.07
     sandals
    0.06
    jících
    0.06
    ?>↵
    0.06
    fill
    0.06
     BT
    0.06
     cott
    0.06
     cheats
    0.06
    Act Density 0.002%

    No Known Activations