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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lic
    -0.06
    》↵
    -0.06
    Alexander
    -0.06
    sei
    -0.06
     geben
    -0.06
    tpl
    -0.06
     -(
    -0.06
    osaurs
    -0.05
     XXX
    -0.05
     серпня
    -0.05
    POSITIVE LOGITS
     tons
    0.07
    تغ
    0.07
     outlaw
    0.07
     ре
    0.07
    (gr
    0.06
     bytesRead
    0.06
    /users
    0.06
    _do
    0.06
    促
    0.06
     SWITCH
    0.06
    Act Density 0.001%

    No Known Activations