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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of the proteasome complex (i.e. subwords of “proteasome”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Glo
    -0.07
     Mesh
    -0.06
     melted
    -0.06
     chlor
    -0.06
    bp
    -0.06
     SPORT
    -0.06
    326
    -0.06
     kterých
    -0.06
     Johnson
    -0.06
     Chlor
    -0.06
    POSITIVE LOGITS
    의
    0.08
    alia
    0.07
    ]});↵
    0.07
    otu
    0.07
     accus
    0.07
    ние
    0.06
     ।↵
    0.06
    uegos
    0.06
    циях
    0.06
    -scal
    0.06
    Act Density 0.001%

    No Known Activations