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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clients
    -0.07
    icast
    -0.06
     insult
    -0.06
    _zoom
    -0.06
    -duty
    -0.06
    (conv
    -0.06
     prep
    -0.06
     Cases
    -0.06
     consent
    -0.06
    PLICATION
    -0.06
    POSITIVE LOGITS
     onay
    0.07
    되는
    0.07
     коман
    0.07
    .rmtree
    0.07
     nodeId
    0.06
     {:?}",
    0.06
     seine
    0.06
    .MESSAGE
    0.06
     unus
    0.06
    bestos
    0.06
    Act Density 0.005%

    No Known Activations