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

    Neuronpedia

    INDEX
    Explanations

    chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     establishes
    -0.08
    VU
    -0.08
    Bas
    -0.08
    献
    -0.08
    طني
    -0.08
    Indirect
    -0.08
    -rata
    -0.07
     entert
    -0.07
     bas
    -0.07
    PAT
    -0.07
    POSITIVE LOGITS
     modifications
    0.08
     الخارجية
    0.08
     Havana
    0.08
     modific
    0.08
     interrog
    0.07
     sequencing
    0.07
     Creme
    0.07
     sequ
    0.07
     synthetic
    0.07
     tweaks
    0.07
    Act Density 0.003%

    No Known Activations