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

    Neuronpedia

    INDEX
    Explanations

    dresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icon
    -0.07
    يق
    -0.07
     EventEmitter
    -0.07
     detention
    -0.06
     NEG
    -0.06
     갖
    -0.06
     buzz
    -0.06
     TER
    -0.06
    .Primary
    -0.06
    مت
    -0.06
    POSITIVE LOGITS
    quisite
    0.07
     hdr
    0.07
     facilitating
    0.06
    akespeare
    0.06
     graceful
    0.06
     lovely
    0.06
    ู
    0.06
    eldon
    0.06
     achieves
    0.06
    StateManager
    0.06
    Act Density 0.006%

    No Known Activations