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

    Neuronpedia

    INDEX
    Explanations

    Technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.68
     AssemblyVersion
    -0.68
     nuages
    -0.65
    -0.63
     tué
    -0.63
    horabuena
    -0.63
    APS
    -0.62
    fjspx
    -0.62
     feroit
    -0.61
    equivalent
    -0.60
    POSITIVE LOGITS
    s
    0.52
    ing
    0.49
    ReadByte
    0.49
    ally
    0.49
    spheric
    0.47
    ly
    0.45
     passt
    0.45
     thoát
    0.45
    df
    0.44
    l
    0.44
    Act Density 0.230%

    No Known Activations