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

    Neuronpedia

    INDEX
    Explanations

    Wanting someone back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정도
    -0.07
     harming
    -0.06
    ừa
    -0.06
    nection
    -0.06
    (""),
    -0.06
     McCabe
    -0.06
     السم
    -0.06
     Beled
    -0.06
    观看
    -0.06
     самое
    -0.06
    POSITIVE LOGITS
    aded
    0.07
    .Flow
    0.07
     yielding
    0.07
     Falls
    0.07
     dying
    0.07
    oll
    0.06
    أس
    0.06
    HI
    0.06
    HC
    0.06
    ins
    0.06
    Act Density 0.042%

    No Known Activations