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

    Neuronpedia

    INDEX
    Explanations

    torch

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “torch.” API calls (i.e. tokens beginning with “torch.”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .flatMap
    -0.08
     AREA
    -0.08
     препара
    -0.07
    amin
    -0.07
    ENDING
    -0.07
    .min
    -0.07
    -boot
    -0.07
    .Bytes
    -0.07
    Division
    -0.07
     quan
    -0.06
    POSITIVE LOGITS
     torch
    0.09
    (torch
    0.09
    =torch
    0.08
     Torch
    0.08
    orch
    0.07
     Ritch
    0.06
    onte
    0.06
    torch
    0.06
    松
    0.06
     Scotch
    0.06
    Act Density 0.003%

    No Known Activations