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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAP
    -0.07
    ByKey
    -0.06
     None
    -0.06
     tutto
    -0.06
    	L
    -0.06
    Sharing
    -0.06
     Evo
    -0.06
     batteries
    -0.06
    _PREVIEW
    -0.06
    _xyz
    -0.06
    POSITIVE LOGITS
    ους
    0.07
    خص
    0.07
    기관
    0.06
    報
    0.06
     speculative
    0.06
     růz
    0.06
    ')}}">
    0.06
    การศ
    0.06
    Recently
    0.06
    )})
    0.06
    Act Density 0.120%

    No Known Activations