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

    Neuronpedia

    INDEX
    Explanations

    likely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anol
    -0.07
     healed
    -0.07
     agon
    -0.07
    wor
    -0.06
     Wor
    -0.06
     sched
    -0.06
     nostra
    -0.06
    ่งชาต
    -0.06
     conservation
    -0.06
     renewable
    -0.06
    POSITIVE LOGITS
    ()),↵
    0.07
     Rosenstein
    0.06
    !!}</
    0.06
    /gl
    0.06
     ]↵
    0.06
    .echo
    0.06
     practice
    0.06
    .modelo
    0.06
    .TEXTURE
    0.06
     آق
    0.06
    Act Density 0.010%

    No Known Activations