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

    Neuronpedia

    INDEX
    Explanations

    Combining different things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    其
    -0.07
     (**
    -0.07
    .selenium
    -0.06
     acidic
    -0.06
     finds
    -0.06
     ==========
    -0.06
    (fmt
    -0.06
    ために
    -0.06
    环
    -0.06
    Key
    -0.06
    POSITIVE LOGITS
     Gabri
    0.08
     Trafford
    0.07
    _CNTL
    0.07
    _CAL
    0.06
    ipped
    0.06
    estado
    0.06
    ｜
    0.06
    ús
    0.06
     subtype
    0.06
     �
    0.06
    Act Density 0.987%

    No Known Activations