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

    Neuronpedia

    INDEX
    Explanations

    Explaining and writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    飲
    -0.07
    šet
    -0.06
     Capcom
    -0.06
    ocaly
    -0.06
    .cover
    -0.06
    (tol
    -0.06
    Hal
    -0.06
     Ip
    -0.06
     replicated
    -0.06
    POSITIVE LOGITS
    ımızın
    0.06
    zl
    0.06
    CREATE
    0.06
    Watching
    0.06
     surgery
    0.06
    letal
    0.06
     drilling
    0.06
     conqu
    0.06
    (bucket
    0.06
    uck
    0.06
    Act Density 0.026%

    No Known Activations