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

    Neuronpedia

    INDEX
    Explanations

    inclusion and exclusion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itol
    -0.08
     �
    -0.07
    沏
    -0.07
    ﳝ
    -0.07
    rzą
    -0.07
     Zus
    -0.07
    geben
    -0.07
    .twimg
    -0.07
    썸
    -0.07
    𬭁
    -0.06
    POSITIVE LOGITS
     motifs
    0.08
     hello
    0.08
     interview
    0.07
     fk
    0.07
    伙伴
    0.07
    懷
    0.07
     happiness
    0.07
     scoring
    0.07
     Hospitality
    0.07
    تا
    0.07
    Act Density 0.014%

    No Known Activations