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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tat
    -0.08
     tục
    -0.07
     scams
    -0.07
    �
    -0.07
     Berm
    -0.06
     Ú
    -0.06
     handful
    -0.06
    !)↵
    -0.06
    엄
    -0.06
    Manage
    -0.06
    POSITIVE LOGITS
    لال
    0.07
     lastIndex
    0.06
    .infinity
    0.06
     Clearance
    0.06
    itness
    0.06
     Čes
    0.06
     stove
    0.06
     marching
    0.06
     emits
    0.06
     dock
    0.06
    Act Density 0.002%

    No Known Activations