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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _physical
    -0.07
     catcher
    -0.06
    roach
    -0.06
    imoto
    -0.06
    арам
    -0.06
    adores
    -0.06
     ostat
    -0.06
    �
    -0.06
    meye
    -0.06
     ста
    -0.06
    POSITIVE LOGITS
     Components
    0.07
     与
    0.07
    	throws
    0.07
    Passwords
    0.07
    	Document
    0.07
    --[
    0.06
    ldata
    0.06
     vog
    0.06
    '],['
    0.06
     Solic
    0.06
    Act Density 0.003%

    No Known Activations