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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setSize
    -0.07
     junction
    -0.07
    чих
    -0.06
    Comments
    -0.06
     모습
    -0.06
     demasi
    -0.06
    食
    -0.06
     rupture
    -0.06
    宅
    -0.06
    Checkpoint
    -0.06
    POSITIVE LOGITS
    นว
    0.07
    ội
    0.07
     exce
    0.06
    picked
    0.06
    /prom
    0.06
    theon
    0.06
    _FB
    0.06
    _EXEC
    0.06
    Adds
    0.06
    akat
    0.06
    Act Density 0.053%

    No Known Activations