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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NoError
    -0.08
    --------------↵
    -0.06
     giants
    -0.06
    (Character
    -0.06
    andReturn
    -0.06
    preci
    -0.06
    (None
    -0.06
    =?",
    -0.06
     "",
↵
    -0.06
    PostalCodes
    -0.06
    POSITIVE LOGITS
    DL
    0.07
    unc
    0.06
    _MASK
    0.06
    -a
    0.06
    іст
    0.06
     individually
    0.06
     كام
    0.06
     HD
    0.06
     quaint
    0.06
     chord
    0.06
    Act Density 0.040%

    No Known Activations