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

    Neuronpedia

    INDEX
    Explanations

    circuits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Circuits
    -1.21
     circuits
    -1.16
     circuit
    -1.07
     CIRCUIT
    -1.07
     Circuit
    -1.05
    Circuit
    -1.05
    circuit
    -1.04
    circuits
    -1.01
     pleaſure
    -0.99
     purpoſe
    -0.96
    POSITIVE LOGITS
     
    0.62
    ing
    0.55
    (
    0.55
     of
    0.54
     M
    0.53
    .
    0.53
     p
    0.52
    ↵↵
    0.50
     how
    0.48
    :
    0.47
    Act Density 1.147%

    No Known Activations