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

    Neuronpedia

    INDEX
    Explanations

    URLs and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Steward
    -0.09
     stewardship
    -0.08
     Informat
    -0.08
    roscopic
    -0.08
     workloads
    -0.08
     Larson
    -0.07
    fahren
    -0.07
     Perth
    -0.07
    experienced
    -0.07
     trabaj
    -0.07
    POSITIVE LOGITS
    AIza
    0.10
    Google
    0.10
     Google
    0.10
    .google
    0.09
    google
    0.09
     Google's
    0.09
    _google
    0.09
    -google
    0.09
    ?q
    0.09
    .baidu
    0.08
    Act Density 0.007%

    No Known Activations