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

    Neuronpedia

    INDEX
    Explanations

    man

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asto
    -0.07
    intr
    -0.07
    TOOLS
    -0.07
    ように
    -0.06
    .loader
    -0.06
     //}↵
    -0.06
    _RO
    -0.06
    {}]
    -0.06
    39
    -0.06
    -keys
    -0.06
    POSITIVE LOGITS
     ornament
    0.07
    월까지
    0.06
     πραγμα
    0.06
    /person
    0.06
    shine
    0.06
     lorem
    0.06
    .Some
    0.06
    ummies
    0.06
    лер
    0.06
     muslim
    0.06
    Act Density 0.005%

    No Known Activations