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

    Neuronpedia

    INDEX
    Explanations

    standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Entry
    -0.07
     akt
    -0.06
     grp
    -0.06
    .place
    -0.06
     occurrence
    -0.06
     filt
    -0.06
    蕉
    -0.06
    responseObject
    -0.06
    _trajectory
    -0.06
     connexion
    -0.06
    POSITIVE LOGITS
     standards
    0.09
     Standards
    0.08
     poorer
    0.07
     Estados
    0.07
    ंड
    0.07
    ublish
    0.06
    監
    0.06
     "'.
    0.06
     verbess
    0.06
     heats
    0.06
    Act Density 0.016%

    No Known Activations