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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -generator
    -0.07
    .content
    -0.06
    dd
    -0.06
    turned
    -0.06
    rowser
    -0.06
    ذر
    -0.06
    ơm
    -0.06
    Turn
    -0.06
    ुक
    -0.06
     dataType
    -0.06
    POSITIVE LOGITS
    []={
    0.07
     Financial
    0.07
     Banks
    0.07
    [left
    0.07
     흐
    0.07
    -all
    0.06
     situace
    0.06
     고개를
    0.06
    ős
    0.06
    ################################
    0.06
    Act Density 0.030%

    No Known Activations