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

    Neuronpedia

    INDEX
    Explanations

    stay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SIMPLE
    -0.06
    (component
    -0.06
     lament
    -0.06
     tee
    -0.06
     hé
    -0.06
    YouTube
    -0.06
    Statement
    -0.06
     mesa
    -0.06
    sq
    -0.06
    ılıyor
    -0.06
    POSITIVE LOGITS
    DCF
    0.07
     molest
    0.06
     pozit
    0.06
     Assad
    0.06
     MILL
    0.06
     grenade
    0.06
    _blob
    0.06
     Sơn
    0.06
    _vlan
    0.06
     RULE
    0.06
    Act Density 0.023%

    No Known Activations