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

    Neuronpedia

    INDEX
    Explanations

    cloud computing and networks

    np_max-act · gemini-2.0-flash

    This neuron fires on words that refer to physical location or movement (e.g., “home,” “commute,” “classroom”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    amb
    -0.07
    #if
    -0.07
    UCT
    -0.07
    _rgba
    -0.06
    isine
    -0.06
     dens
    -0.06
    卓
    -0.06
     ragazze
    -0.06
    産
    -0.06
    Pers
    -0.06
    POSITIVE LOGITS
    ="/">↵
    0.07
    调查
    0.06
    .loaded
    0.06
    /high
    0.06
    .ingredients
    0.06
    -badge
    0.06
     plugged
    0.06
    UniformLocation
    0.06
    	Local
    0.06
    jab
    0.05
    Act Density 0.058%

    No Known Activations