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

    Neuronpedia

    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERC
    -0.07
    eníze
    -0.07
     οργ
    -0.06
     receives
    -0.06
     относ
    -0.06
    lopen
    -0.06
     slew
    -0.06
    Sel
    -0.06
     �
    -0.06
    plně
    -0.06
    POSITIVE LOGITS
     Modification
    0.06
     Version
    0.06
    Hidden
    0.06
     LI
    0.06
    _METHOD
    0.06
     upgraded
    0.06
     Img
    0.06
    .Creator
    0.06
     Novel
    0.05
    Feedback
    0.05
    Act Density 0.069%

    No Known Activations