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

    Neuronpedia

    INDEX
    Explanations

    vacation rental descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ihm
    -0.07
    Technology
    -0.06
     дозволя
    -0.06
     distur
    -0.06
     Lesbian
    -0.06
     دل
    -0.06
    edy
    -0.06
     Tight
    -0.06
     sns
    -0.06
     intimid
    -0.06
    POSITIVE LOGITS
     �
    0.07
     DWC
    0.07
    _ALWAYS
    0.07
    лаз
    0.06
    .Dev
    0.06
    ög
    0.06
     lệ
    0.06
    _traffic
    0.06
    .Spec
    0.06
     секрет
    0.06
    Act Density 0.073%

    No Known Activations