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

    Neuronpedia

    INDEX
    Explanations

    programming/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    也有
    -0.07
     accurate
    -0.07
     ads
    -0.06
     pl
    -0.06
     intensity
    -0.06
     really
    -0.06
     caut
    -0.06
    олит
    -0.06
     efficient
    -0.06
     centroid
    -0.06
    POSITIVE LOGITS
    .aggregate
    0.09
    currentState
    0.07
    .Xr
    0.07
    ntity
    0.07
    _<?
    0.07
    _Stream
    0.07
    .:.:.:.:.:.:.:.:
    0.06
     esac
    0.06
    register
    0.06
     Plastic
    0.06
    Act Density 0.000%

    No Known Activations