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

    Neuronpedia

    INDEX
    Explanations

    Code/technical and "fire"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pie
    -0.07
    ']]);↵
    -0.07
     ogs
    -0.07
    ]]);↵
    -0.06
     chút
    -0.06
     teil
    -0.06
     gad
    -0.06
     affid
    -0.06
     ethnic
    -0.06
     zest
    -0.06
    POSITIVE LOGITS
     sonrasında
    0.07
     lire
    0.07
     saline
    0.07
    FF
    0.07
     disclose
    0.07
     MIPS
    0.06
    McC
    0.06
    ActionCreators
    0.06
     ObjectOutputStream
    0.06
    arena
    0.06
    Act Density 0.000%

    No Known Activations