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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Αρ
    -0.07
     mou
    -0.07
     RadioButton
    -0.06
     CAS
    -0.06
     skinny
    -0.06
    战争
    -0.06
     hỗn
    -0.06
     Heal
    -0.06
     ud
    -0.06
     살
    -0.06
    POSITIVE LOGITS
    /content
    0.07
    вид
    0.06
    technical
    0.06
    Street
    0.06
    wrapper
    0.06
    َح
    0.06
     міся
    0.06
    мос
    0.06
    mAh
    0.06
    dee
    0.06
    Act Density 0.000%

    No Known Activations