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

    Neuronpedia

    INDEX
    Explanations

    Lady Finger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2130>
    0.64
    <unused2164>
    0.63
    ভিয়েতনাম
    0.59
     allergies
    0.58
    
    0.58
    푞
    0.57
    <unused398>
    0.57
    <unused1854>
    0.57
     vattum
    0.56
    <unused193>
    0.56
    POSITIVE LOGITS
    U
    0.76
    T
    0.73
    V
    0.73
    F
    0.72
    M
    0.71
     B
    0.70
    G
    0.70
     F
    0.69
    H
    0.69
    O
    0.69
    Act Density 22.152%

    No Known Activations