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

    Neuronpedia

    INDEX
    Explanations

    Sentence endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .todo
    -0.07
    κυ
    -0.07
     scoff
    -0.07
     Место
    -0.06
     wash
    -0.06
    OSH
    -0.06
    лиш
    -0.06
    sessions
    -0.06
    lucent
    -0.06
    たら
    -0.06
    POSITIVE LOGITS
    stellung
    0.06
     göç
    0.06
     Cros
    0.06
     För
    0.06
    _Field
    0.06
     bak
    0.06
     constr
    0.06
     {

↵
    0.06
     Rover
    0.06
     spp
    0.05
    Act Density 0.039%

    No Known Activations