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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afs
    -0.08
    侄
    -0.08
    鬟
    -0.07
    嗉
    -0.07
    ません
    -0.07
     gastr
    -0.07
    ǘ
    -0.07
     compos
    -0.07
     immense
    -0.07
    AxisSize
    -0.07
    POSITIVE LOGITS
     isolate
    0.08
     ecx
    0.07
    利用
    0.07
     assessed
    0.07
    ㊞
    0.07
     studied
    0.07
    >'↵
    0.07
    }});↵
    0.07
     tapping
    0.07
     Word
    0.07
    Act Density 0.003%

    No Known Activations