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

    Neuronpedia

    INDEX
    Explanations

    ],

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anger
    -0.07
     =================================
    -0.07
    onclick
    -0.06
     Ahmed
    -0.06
    	B
    -0.06
    ------------------------------------------------
    -0.06
    ？↵↵
    -0.06
    藍
    -0.06
    Text
    -0.06
    --}}↵
    -0.06
    POSITIVE LOGITS
     Yorkshire
    0.07
     Inserts
    0.07
     listings
    0.07
    tls
    0.07
    .timedelta
    0.06
     Overflow
    0.06
    ilip
    0.06
     ratings
    0.06
     Gamma
    0.06
     polyester
    0.06
    Act Density 0.013%

    No Known Activations