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

    Neuronpedia

    INDEX
    Explanations

    Code/Equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Form
    -0.07
    iculo
    -0.07
    credit
    -0.07
    .writeFileSync
    -0.07
     otras
    -0.06
    (signal
    -0.06
    eworld
    -0.06
     amusement
    -0.06
    .…
    -0.06
    /ar
    -0.06
    POSITIVE LOGITS
    🦑
    0.08
     yaml
    0.07
     Kotlin
    0.07
    _KERNEL
    0.07
     consecutive
    0.07
     possible
    0.07
     możliwe
    0.07
     CLK
    0.06
     DLL
    0.06
    Constraints
    0.06
    Act Density 0.000%

    No Known Activations