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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mayor
    -0.06
     Rit
    -0.06
     slime
    -0.06
     Alto
    -0.06
     شکن
    -0.06
     kredi
    -0.06
    /disable
    -0.06
    �
    -0.06
     Mine
    -0.06
     засід
    -0.06
    POSITIVE LOGITS
    peer
    0.06
    upgrade
    0.06
     acompañ
    0.06
     Beam
    0.06
     erotica
    0.06
    key
    0.06
    86
    0.06
     stray
    0.06
    27
    0.06
    OfBirth
    0.06
    Act Density 0.002%

    No Known Activations