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

    Neuronpedia

    INDEX
    Explanations

    cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zar
    -0.07
     strongest
    -0.07
    iples
    -0.06
    ただ
    -0.06
     Arap
    -0.06
     Narc
    -0.06
     Had
    -0.06
     prosecute
    -0.06
    া�
    -0.06
     extrad
    -0.06
    POSITIVE LOGITS
    dain
    0.07
    _months
    0.07
     libero
    0.06
    _FOLDER
    0.06
    -if
    0.06
     paid
    0.06
     shorthand
    0.06
    _codegen
    0.06
    registered
    0.06
    jer
    0.06
    Act Density 0.002%

    No Known Activations