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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offensive
    -0.07
     فوتبال
    -0.07
    Pic
    -0.07
     detain
    -0.07
     camps
    -0.07
    Canvas
    -0.07
    医
    -0.06
     commit
    -0.06
     pilot
    -0.06
    らい
    -0.06
    POSITIVE LOGITS
     ell
    0.07
     Unc
    0.07
    ],$
    0.06
    atoire
    0.06
     Equ
    0.06
    ued
    0.06
    jual
    0.06
     geb
    0.06
    -esque
    0.06
    LARI
    0.06
    Act Density 0.036%

    No Known Activations