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

    Neuronpedia

    INDEX
    Explanations

    micro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     смот
    -0.07
     �
    -0.06
     lotion
    -0.06
    Vm
    -0.06
     onComplete
    -0.06
     Однако
    -0.06
    LTE
    -0.06
     Treaty
    -0.06
    Question
    -0.06
    kw
    -0.06
    POSITIVE LOGITS
     plagiar
    0.06
    cells
    0.06
     attributed
    0.06
    _gem
    0.06
     Δη
    0.06
    aint
    0.06
    well
    0.06
    els
    0.06
    ülü
    0.06
    .metamodel
    0.06
    Act Density 0.028%

    No Known Activations