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

    Neuronpedia

    INDEX
    Explanations

    and/with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     интер
    -0.07
     projectName
    -0.07
    _probability
    -0.07
     impl
    -0.06
     الجام
    -0.06
     котор
    -0.06
     Griffin
    -0.06
     �
    -0.06
     �
    -0.06
     eggs
    -0.06
    POSITIVE LOGITS
    览
    0.06
     boils
    0.06
    plorer
    0.06
    osi
    0.06
    worthy
    0.06
    identally
    0.06
    osit
    0.06
    із
    0.06
    emer
    0.06
     roleId
    0.06
    Act Density 0.022%

    No Known Activations