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

    Neuronpedia

    INDEX
    Explanations

    milestones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }}">{{
    -0.07
    (qu
    -0.07
    акон
    -0.07
    //"
    -0.06
     Hunting
    -0.06
     altar
    -0.06
    μάτων
    -0.06
    resses
    -0.06
    AREN
    -0.06
    [".
    -0.06
    POSITIVE LOGITS
     využití
    0.07
     FRA
    0.06
     infra
    0.06
     CNS
    0.06
    frag
    0.06
    atial
    0.06
    656
    0.05
     Ryder
    0.05
     Maver
    0.05
    одав
    0.05
    Act Density 0.133%

    No Known Activations