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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cam
    -0.07
     Opr
    -0.07
    ths
    -0.06
    군요
    -0.06
    .ut
    -0.06
     pedals
    -0.06
    �
    -0.06
    Ide
    -0.06
    ются
    -0.06
    ดา
    -0.06
    POSITIVE LOGITS
     چ
    0.07
     fines
    0.07
    ünden
    0.06
    جار
    0.06
     fest
    0.06
    884
    0.06
    ZN
    0.06
     ورزش
    0.06
     mum
    0.06
    ("{\"
    0.06
    Act Density 0.006%

    No Known Activations