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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wa
    -0.07
     disconnected
    -0.07
     designate
    -0.07
     North
    -0.07
     occasional
    -0.07
     neuro
    -0.07
    (word
    -0.06
    ,k
    -0.06
     grandparents
    -0.06
     sociology
    -0.06
    POSITIVE LOGITS
    ğer
    0.07
    insics
    0.06
    _BLE
    0.06
    ascade
    0.06
    URRENCY
    0.06
     προϊ
    0.06
    ntity
    0.06
    ÖL
    0.06
    /App
    0.06
    ~↵↵
    0.06
    Act Density 0.048%

    No Known Activations