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

    Neuronpedia

    INDEX
    Explanations

    audiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     마
    -0.07
     Ran
    -0.07
    打
    -0.06
     soldier
    -0.06
    のも
    -0.06
     黑
    -0.06
    atro
    -0.06
     �
    -0.06
     Mur
    -0.06
     město
    -0.06
    POSITIVE LOGITS
    Version
    0.07
    -php
    0.07
     القد
    0.07
    CCCC
    0.06
     Doctrine
    0.06
     ذلك
    0.06
     attainment
    0.06
               
    0.06
    dbname
    0.06
     enim
    0.06
    Act Density 0.079%

    No Known Activations