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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    efon
    -0.07
    addock
    -0.07
    ربی
    -0.06
    ustral
    -0.06
    �
    -0.06
    _DIALOG
    -0.06
     фин
    -0.06
    scheduled
    -0.06
    vní
    -0.06
     Heather
    -0.06
    POSITIVE LOGITS
    /photo
    0.07
     experimented
    0.07
     covid
    0.06
    Operating
    0.06
    ρ
    0.06
    sav
    0.06
     took
    0.06
     Additional
    0.06
     ~
    0.06
     vowels
    0.06
    Act Density 0.004%

    No Known Activations