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

    Neuronpedia

    INDEX
    Explanations

    *c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bal
    -0.07
     calculus
    -0.07
    蓝图
    -0.07
    categoria
    -0.07
    𝙇
    -0.07
    	x
    -0.07
     Arcade
    -0.07
    のです
    -0.07
    就得
    -0.07
     translation
    -0.07
    POSITIVE LOGITS
    ˻
    0.09
     מהווה
    0.08
     manière
    0.07
     ((__
    0.07
    /group
    0.07
     встреча
    0.07
    ᇂ
    0.06
     projectName
    0.06
     потеря
    0.06
     rapes
    0.06
    Act Density 0.001%

    No Known Activations