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

    Neuronpedia

    INDEX
    Explanations

    chained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dět
    -0.07
    	sf
    -0.06
    _CB
    -0.06
     Shock
    -0.06
     promotes
    -0.06
    	com
    -0.06
    protect
    -0.06
     надо
    -0.06
    ;o
    -0.06
     atmos
    -0.06
    POSITIVE LOGITS
    _bases
    0.07
    ينه
    0.07
    埋
    0.07
    ovable
    0.06
     geme
    0.06
    /log
    0.06
    alloc
    0.06
    thought
    0.06
     indicative
    0.06
     männ
    0.06
    Act Density 0.000%

    No Known Activations