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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     displacement
    -0.28
    庸
    -0.26
     displ
    -0.26
    å±ħ
    -0.25
     corresponding
    -0.25
    绦
    -0.24
    Should
    -0.24
    ope
    -0.24
    epy
    -0.24
    should
    -0.23
    POSITIVE LOGITS
    abol
    0.26
    branches
    0.26
    amel
    0.25
    åĮ¹
    0.25
    izzard
    0.24
    ahl
    0.24
     rele
    0.24
    mer
    0.24
    çļĦæķ´ä½ĵ
    0.24
     ind
    0.23
    Act Density 0.044%

    No Known Activations