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

    Neuronpedia

    INDEX
    Explanations

    Data representation

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens (all activations are zero).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    λλην
    -0.06
    िलत
    -0.06
     suger
    -0.06
     메
    -0.06
     Yak
    -0.06
    	builder
    -0.06
     日期
    -0.06
     Davies
    -0.06
     afterEach
    -0.06
     curso
    -0.06
    POSITIVE LOGITS
    .How
    0.07
     existing
    0.07
     primeira
    0.07
    November
    0.07
    Activation
    0.07
    ギ
    0.07
    _dims
    0.06
     disp
    0.06
    -width
    0.06
    faces
    0.06
    Act Density 0.015%

    No Known Activations