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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Overflow
    -0.07
     Streams
    -0.07
    _policy
    -0.06
    -powered
    -0.06
    _pack
    -0.06
     sleeping
    -0.06
    	channel
    -0.06
    15
    -0.06
     canada
    -0.06
     Trump
    -0.06
    POSITIVE LOGITS
    InInspector
    0.06
    ,map
    0.06
    ่าวว
    0.06
    immutable
    0.06
     районе
    0.06
    ekkür
    0.06
    Transient
    0.06
     herramient
    0.06
     uplifting
    0.06
    žel
    0.06
    Act Density 0.150%

    No Known Activations