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

    Neuronpedia

    INDEX
    Explanations

    code references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vir
    -0.07
    perienced
    -0.07
    +".
    -0.06
    età
    -0.06
    𝓵
    -0.06
    (Audio
    -0.06
    	events
    -0.06
     [-
    -0.06
     ved
    -0.06
     вы
    -0.06
    POSITIVE LOGITS
     property
    0.08
    继承
    0.08
    atz
    0.07
    anny
    0.06
    repos
    0.06
    thren
    0.06
     array
    0.06
     AppComponent
    0.06
    赞扬
    0.06
    魍
    0.06
    Act Density 0.001%

    No Known Activations