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

    Neuronpedia

    INDEX
    Explanations

    trouble with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neka
    0.49
    ו
    0.47
     kole
    0.46
     zid
    0.46
     gleichen
    0.45
     tipos
    0.45
     aceea
    0.44
    ודה
    0.44
     tipp
    0.43
     andra
    0.43
    POSITIVE LOGITS
     EVP
    0.47
     externalities
    0.45
     allusion
    0.43
     overw
    0.43
     secrecy
    0.42
     overwritten
    0.41
     HW
    0.41
     introspection
    0.41
     VU
    0.40
     inhabit
    0.40
    Act Density 0.000%

    No Known Activations