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

    Neuronpedia

    INDEX
    Explanations

    iron

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vos
    -0.07
    ipients
    -0.07
    冬
    -0.07
    apis
    -0.07
    valuate
    -0.06
    -lfs
    -0.06
     đảo
    -0.06
    quis
    -0.06
    icts
    -0.06
    uelve
    -0.06
    POSITIVE LOGITS
     enemy
    0.07
     simplest
    0.07
     Dynam
    0.07
     coding
    0.06
     conditional
    0.06
     JPanel
    0.06
     BRAND
    0.06
     whose
    0.06
     behaviors
    0.06
                                                ↵
    0.06
    Act Density 0.014%

    No Known Activations