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

    Neuronpedia

    INDEX
    Explanations

    Managing emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ACS
    -0.08
     bx
    -0.07
     fv
    -0.07
     Munich
    -0.07
    -0.07
     Admiral
    -0.07
    圆
    -0.07
     <>
    -0.07
     magnets
    -0.07
    ]];↵
    -0.07
    POSITIVE LOGITS
    ocator
    0.07
     Variant
    0.07
    bilit
    0.07
     oppress
    0.07
    渐
    0.07
     opacity
    0.07
    迦
    0.07
     Psychiat
    0.07
     generator
    0.06
    (history
    0.06
    Act Density 0.040%

    No Known Activations