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

    Neuronpedia

    INDEX
    Explanations

    delimiter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coordinates
    -0.06
    _fail
    -0.06
     základě
    -0.06
     fund
    -0.06
     incapac
    -0.06
    (bs
    -0.06
     faith
    -0.06
     Fund
    -0.06
     Games
    -0.06
    Rows
    -0.06
    POSITIVE LOGITS
     ===>
    0.07
    adě
    0.07
     sep
    0.07
     delimiter
    0.06
     zby
    0.06
    BB
    0.06
     реб
    0.06
    ETHER
    0.06
    INPUT
    0.06
    ibel
    0.06
    Act Density 0.007%

    No Known Activations