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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imagination
    -0.07
     -------↵
    -0.06
    ıldığında
    -0.06
    ■
    -0.06
    +j
    -0.06
     meds
    -0.06
    (fil
    -0.06
     IOError
    -0.06
     Captain
    -0.06
    933
    -0.06
    POSITIVE LOGITS
    reuse
    0.08
    lanmış
    0.07
    078
    0.07
    스코
    0.07
    576
    0.07
     university
    0.07
    �
    0.07
     InetAddress
    0.07
    �
    0.07
     어�
    0.06
    Act Density 0.098%

    No Known Activations