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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     위한
    -0.06
     свого
    -0.06
     cache
    -0.06
    ihan
    -0.05
    Sites
    -0.05
    idences
    -0.05
    .='<
    -0.05
     sebuah
    -0.05
     رب
    -0.05
     dělat
    -0.05
    POSITIVE LOGITS
     PA
    0.08
     ANSI
    0.08
     sqrt
    0.07
     condemn
    0.07
    ]
    0.07
    (instr
    0.07
    -command
    0.07
    _alpha
    0.07
     anyone
    0.07
    (part
    0.07
    Act Density 0.001%

    No Known Activations