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

    Neuronpedia

    INDEX
    Explanations

    text art symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tareas
    0.31
    უცი
    0.29
    ேத்க
    0.27
    ⸩
    0.27
    äische
    0.26
     예측
    0.26
    轫
    0.26
    ంబేద్కర్
    0.26
    巅峰
    0.26
    勍
    0.26
    POSITIVE LOGITS
    0.36
     B
    0.36
    1
    0.35
     L
    0.34
     l
    0.34
     $
    0.33
     A
    0.32
     N
    0.31
     P
    0.30
    2
    0.30
    Act Density 0.016%

    No Known Activations