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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lists
    -0.07
    /sites
    -0.07
    .over
    -0.06
    /global
    -0.06
    켜
    -0.06
     agrees
    -0.06
    وة
    -0.06
    XYZ
    -0.06
    swith
    -0.06
    _Read
    -0.06
    POSITIVE LOGITS
     consts
    0.07
     need
    0.06
     "",↵
    0.06
     Soviets
    0.06
    �
    0.06
    terraform
    0.06
    declare
    0.06
     том
    0.05
     TArray
    0.05
     Conv
    0.05
    Act Density 0.011%

    No Known Activations