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

    Neuronpedia

    INDEX
    Explanations

    fuel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _aux
    -0.07
    ському
    -0.07
    ける
    -0.06
     flag
    -0.06
    Τα
    -0.06
    (dialog
    -0.06
    ？↵↵
    -0.06
    ской
    -0.06
     Ko
    -0.06
    quet
    -0.06
    POSITIVE LOGITS
     σει
    0.07
    (metrics
    0.06
    ANTS
    0.06
     punches
    0.06
    .volley
    0.06
    τικός
    0.06
     происходит
    0.06
     Hole
    0.06
    ़ि
    0.06
    .preference
    0.06
    Act Density 0.036%

    No Known Activations