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

    Neuronpedia

    INDEX
    Explanations

    mechanical parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    θρώ
    -0.07
    pr
    -0.06
     marg
    -0.06
    ATION
    -0.06
    _RET
    -0.06
    eyle
    -0.06
    �
    -0.06
     unterstüt
    -0.06
     TRADE
    -0.06
    Marg
    -0.06
    POSITIVE LOGITS
     Adding
    0.07
     Gives
    0.07
    ออก
    0.07
    ován
    0.07
    thermal
    0.06
    Connected
    0.06
     identifies
    0.06
    Funny
    0.06
    acea
    0.06
     Ports
    0.06
    Act Density 0.031%

    No Known Activations