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

    Neuronpedia

    INDEX
    Explanations

    say the ending -ade

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feeling
    -0.06
     restoration
    -0.06
     jsme
    -0.06
    kc
    -0.06
    atomy
    -0.06
    ेस
    -0.06
     sentenced
    -0.06
     hospitality
    -0.05
    uite
    -0.05
     eylem
    -0.05
    POSITIVE LOGITS
     трех
    0.08
     역
    0.07
    نویس
    0.07
    반기
    0.07
     Torres
    0.07
    .theta
    0.07
     �
    0.07
     것도
    0.07
    .ReadString
    0.07
     Σα
    0.07
    Act Density 0.002%

    No Known Activations