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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     variable
    -0.07
     dynasty
    -0.07
    沈
    -0.07
    rust
    -0.07
     провед
    -0.07
     convex
    -0.07
     Cinder
    -0.07
     invade
    -0.07
     Secrets
    -0.07
     overwhelm
    -0.07
    POSITIVE LOGITS
    aton
    0.09
    ौं
    0.08
    campo
    0.07
    atch
    0.07
    @"↵
    0.06
    ::$_
    0.06
    ÖL
    0.06
    .annotation
    0.06
    TON
    0.06
    .cgColor
    0.06
    Act Density 0.005%

    No Known Activations