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

    Neuronpedia

    INDEX
    Explanations

    _mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intricate
    -0.06
     Combo
    -0.06
    stanov
    -0.06
    ijken
    -0.06
     Halk
    -0.06
    _os
    -0.06
    ollo
    -0.05
    yne
    -0.05
    ites
    -0.05
    　　 　 　
    -0.05
    POSITIVE LOGITS
     bear
    0.07
    (tree
    0.07
    ..<
    0.07
     read
    0.07
     employing
    0.07
     pray
    0.07
     usually
    0.07
    mentation
    0.07
    .erase
    0.07
     limiting
    0.06
    Act Density 0.000%

    No Known Activations