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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endings
    -0.07
     narciss
    -0.06
     wife
    -0.06
    Them
    -0.06
     paste
    -0.06
    ."↵↵↵
    -0.06
     Brid
    -0.06
    alem
    -0.06
     AVAILABLE
    -0.06
     getChild
    -0.06
    POSITIVE LOGITS
    formation
    0.07
    .kafka
    0.06
     assignable
    0.06
     Depth
    0.06
     yytype
    0.06
    subs
    0.06
    iske
    0.06
    .conn
    0.06
     Enh
    0.06
     qualité
    0.06
    Act Density 0.014%

    No Known Activations