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

    Neuronpedia

    INDEX
    Explanations

    oints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    štění
    -0.08
    픽
    -0.08
    иль
    -0.08
     Clin
    -0.08
    폐
    -0.07
     Bayesian
    -0.07
     Malware
    -0.07
     clin
    -0.07
    扶
    -0.07
    जिस
    -0.07
    POSITIVE LOGITS
     disappointment
    0.14
     disappoint
    0.13
     disappointing
    0.12
     disappointed
    0.11
     enttä
    0.10
     preconce
    0.09
    掉
    0.08
    unity
    0.08
    uracion
    0.08
     setbacks
    0.08
    Act Density 0.007%

    No Known Activations