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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guard
    -0.07
    แนะนำ
    -0.07
     waist
    -0.06
     Bewert
    -0.06
     sew
    -0.06
    Update
    -0.06
    ذكر
    -0.06
     weitere
    -0.06
    -phone
    -0.06
     Before
    -0.06
    POSITIVE LOGITS
    igmatic
    0.07
     libido
    0.07
     profesyonel
    0.07
    PosY
    0.07
    _capability
    0.07
     MouseEventArgs
    0.06
     آزم
    0.06
    .bat
    0.06
     drip
    0.06
    ercial
    0.06
    Act Density 0.003%

    No Known Activations