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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ต
    -0.06
    <State
    -0.06
     Accessibility
    -0.06
    wild
    -0.06
    密
    -0.06
    	URL
    -0.06
     bek
    -0.06
    (state
    -0.06
     PROJECT
    -0.06
    WHAT
    -0.06
    POSITIVE LOGITS
    .exe
    0.07
    lava
    0.06
    nant
    0.06
    uco
    0.06
    nehmer
    0.06
     recher
    0.06
     underscores
    0.06
    Cou
    0.06
    orary
    0.06
    /un
    0.06
    Act Density 0.017%

    No Known Activations