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

    Neuronpedia

    INDEX
    Explanations

    say "wrong"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิถ
    -0.07
    Philadelphia
    -0.07
     İtalya
    -0.06
    men
    -0.06
     Benny
    -0.06
     ofApp
    -0.06
    (pts
    -0.06
     公司
    -0.06
    }});↵
    -0.06
    /connection
    -0.06
    POSITIVE LOGITS
     đăng
    0.06
     Expression
    0.06
    atcher
    0.06
     directly
    0.06
     PIE
    0.06
    .Att
    0.06
     emot
    0.06
     pla
    0.06
    .each
    0.06
     hoặc
    0.06
    Act Density 0.027%

    No Known Activations