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

    Neuronpedia

    INDEX
    Explanations

    radio

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sequence
    -0.07
    _locator
    -0.07
    单位
    -0.07
    想不到
    -0.07
     anywhere
    -0.07
    (INT
    -0.06
    ⻁
    -0.06
    率达到
    -0.06
    abr
    -0.06
    企业和
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Yemen
    0.07
    رو
    0.07
    饥
    0.07
    fp
    0.07
    entry
    0.07
    leton
    0.07
    _poll
    0.06
    	api
    0.06
     ipv
    0.06
    Act Density 0.009%

    No Known Activations