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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propagation
    -0.06
     forces
    -0.06
     Viewing
    -0.06
    منی
    -0.06
     patches
    -0.06
     methods
    -0.06
     swift
    -0.06
     localtime
    -0.06
    xae
    -0.06
     rat
    -0.06
    POSITIVE LOGITS
     build
    0.07
    �
    0.07
     Attach
    0.07
     уменьш
    0.06
     Collabor
    0.06
     Ampl
    0.06
    ा।
    0.06
    classic
    0.06
    TRACT
    0.06
     etiqu
    0.06
    Act Density 0.021%

    No Known Activations