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

    Neuronpedia

    INDEX
    Explanations

    Southwest heter Brand tails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.78
    in
    0.67
    on
    0.56
    spare
    0.54
    u
    0.54
    1
    0.54
    unt
    0.54
     gestellt
    0.53
    element
    0.53
    wrap
    0.53
    POSITIVE LOGITS
    ého
    0.66
     coefficients
    0.57
     abdom
    0.56
     ethyl
    0.55
     efficiencies
    0.55
     outages
    0.55
     erections
    0.54
     quenching
    0.54
     ()=>
    0.54
     canvases
    0.53
    Act Density 0.000%

    No Known Activations