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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .go
    -0.07
    Uploader
    -0.07
    NamedQuery
    -0.06
     urban
    -0.06
     oi
    -0.06
    /high
    -0.06
     Ru
    -0.06
    localhost
    -0.06
    /screen
    -0.06
     conspiracy
    -0.06
    POSITIVE LOGITS
     kann
    0.07
    itionally
    0.06
    �
    0.06
     tet
    0.06
    을
    0.06
     Appro
    0.06
     Drawing
    0.06
     hisset
    0.06
     종
    0.06
    kl
    0.06
    Act Density 0.000%

    No Known Activations