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

    Neuronpedia

    INDEX
    Explanations

    Avoid Contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pub
    0.52
     app
    0.51
    PU
    0.50
    0
    0.46
    K
    0.45
     App
    0.45
    VW
    0.45
    VE
    0.44
    App
    0.43
    SP
    0.43
    POSITIVE LOGITS
     আশ্বাস
    0.51
     acteurs
    0.50
    мас
    0.49
     mejoras
    0.47
     statesmen
    0.47
     médecins
    0.47
     profesores
    0.47
    лық
    0.46
    பிலோ
    0.46
    ить
    0.46
    Act Density 0.001%

    No Known Activations