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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    слуша
    -0.08
    '}}>↵
    -0.07
    ";//
    -0.07
     האלו
    -0.07
     .*
    -0.07
    以上の
    -0.07
    .TypeOf
    -0.07
    中に
    -0.07
    (',');↵
    -0.07
     kvinna
    -0.07
    POSITIVE LOGITS
    ህ
    0.08
    Tank
    0.08
    mel
    0.08
     casual
    0.08
     helmets
    0.08
    ASH
    0.07
     undert
    0.07
     crash
    0.07
    悠
    0.07
    PEED
    0.07
    Act Density 0.027%

    No Known Activations