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

    Neuronpedia

    INDEX
    Explanations

    degrees Fahrenheit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    담당
    -0.07
    fluid
    -0.07
    but
    -0.07
    ランド
    -0.06
     humid
    -0.06
     reluctance
    -0.06
    迪拜
    -0.06
    agua
    -0.06
     tasting
    -0.06
    资本
    -0.06
    POSITIVE LOGITS
     ske
    0.08
    捯
    0.08
    gregated
    0.07
     העוב
    0.07
    (tr
    0.07
    OTHER
    0.07
    onte
    0.07
    בוה
    0.07
    הול
    0.06
    ቀ
    0.06
    Act Density 0.002%

    No Known Activations