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

    Neuronpedia

    INDEX
    Explanations

    bonus points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ุ่
    -0.07
     силь
    -0.07
     setDescription
    -0.07
    受
    -0.07
     розвит
    -0.07
     vap
    -0.07
    defaultValue
    -0.06
    fld
    -0.06
     ú
    -0.06
     savedInstanceState
    -0.06
    POSITIVE LOGITS
     Jurassic
    0.06
    athon
    0.06
     mentions
    0.06
    cción
    0.06
     dříve
    0.06
     matching
    0.06
     boast
    0.06
    thag
    0.06
    ertest
    0.06
    ...
    0.06
    Act Density 0.005%

    No Known Activations