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

    Neuronpedia

    INDEX
    Explanations

    graph theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .util
    -0.08
     Walgreens
    -0.08
    💕
    -0.08
    Won
    -0.08
    Benef
    -0.07
     LETTER
    -0.07
    iphone
    -0.07
     elapsed
    -0.07
     buttery
    -0.07
     megap
    -0.07
    POSITIVE LOGITS
     disrupting
    0.11
     remov
    0.10
     removal
    0.09
     disconnect
    0.09
    Removing
    0.09
     disabling
    0.09
     Removal
    0.09
     제거
    0.09
     incapac
    0.09
     denying
    0.09
    Act Density 0.007%

    No Known Activations