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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     爱
    -0.07
    ams
    -0.07
     herself
    -0.06
     rept
    -0.06
     мар
    -0.06
     Payne
    -0.06
     ब
    -0.06
     chemical
    -0.06
    iento
    -0.06
    _ENGINE
    -0.06
    POSITIVE LOGITS
     azt
    0.06
     Republic
    0.06
    นๆ
    0.06
     tactics
    0.06
    REFIX
    0.06
     ngược
    0.06
    support
    0.06
     static
    0.06
    -register
    0.05
    /back
    0.05
    Act Density 0.090%

    No Known Activations