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

    Neuronpedia

    INDEX
    Explanations

    voice of reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     claiming
    -0.08
     thousands
    -0.08
    .claim
    -0.08
     వేల
    -0.08
     sovereign
    -0.08
     ACL
    -0.08
     January
    -0.08
     ప్రకట
    -0.07
     Thousands
    -0.07
    .baomidou
    -0.07
    POSITIVE LOGITS
    boarding
    0.10
    τισ
    0.09
    -help
    0.08
     aporta
    0.08
     mediation
    0.08
    意见
    0.08
    出现
    0.08
    -prev
    0.08
     virtues
    0.08
     ánimo
    0.08
    Act Density 0.032%

    No Known Activations