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

    Neuronpedia

    INDEX
    Explanations

    MK/MKS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    648
    -0.07
    _userdata
    -0.07
     Emm
    -0.07
    AGENT
    -0.07
    -face
    -0.07
     THERE
    -0.07
    agens
    -0.06
    /type
    -0.06
    696
    -0.06
     Sheldon
    -0.06
    POSITIVE LOGITS
     μέρος
    0.06
     Authorized
    0.06
     discretionary
    0.06
     росій
    0.06
     суспіль
    0.06
     OUTPUT
    0.06
     душ
    0.06
    Compilation
    0.06
    İş
    0.06
     AssemblyDescription
    0.06
    Act Density 0.099%

    No Known Activations