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

    Neuronpedia

    INDEX
    Explanations

    Code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PRESENT
    -0.08
    そう
    -0.06
     Russian
    -0.06
     Autof
    -0.06
    Expect
    -0.06
     Inf
    -0.06
     surround
    -0.06
     insult
    -0.06
     werd
    -0.06
     филь
    -0.06
    POSITIVE LOGITS
     ML
    0.07
    nelle
    0.06
    .yahoo
    0.06
     حرفه
    0.06
     Irene
    0.06
    ницу
    0.06
    ným
    0.06
     Elizabeth
    0.06
     Townsend
    0.06
    <Rigidbody
    0.06
    Act Density 0.000%

    No Known Activations