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

    Neuronpedia

    INDEX
    Explanations

    invariant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Seconds
    -0.07
     wf
    -0.07
    .ArrayList
    -0.06
     Feet
    -0.06
     fragile
    -0.06
    zx
    -0.06
    +"<
    -0.06
     reluct
    -0.06
     pierws
    -0.06
    _digits
    -0.06
    POSITIVE LOGITS
     invariant
    0.08
     留
    0.07
     injector
    0.06
    ays
    0.06
    HUD
    0.06
     evenly
    0.06
     parchment
    0.06
    .JsonProperty
    0.06
    ava
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations