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

    Neuronpedia

    INDEX
    Explanations

    Technical and formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    ilder
    -0.06
    thro
    -0.06
     SOUR
    -0.06
     крас
    -0.06
     Sand
    -0.06
    _middle
    -0.06
    .DAL
    -0.06
     SECOND
    -0.06
     Picker
    -0.06
    POSITIVE LOGITS
     basically
    0.07
    amy
    0.07
     asked
    0.07
    <bool
    0.06
     rpc
    0.06
     ⌒
    0.06
    invalidate
    0.06
    _wf
    0.06
     [=[
    0.06
     tas
    0.06
    Act Density 0.000%

    No Known Activations