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

    Neuronpedia

    INDEX
    Explanations

    describing words after common connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concentrating
    0.42
     concentration
    0.42
     statistical
    0.42
     concentração
    0.42
     shod
    0.40
     hopelessness
    0.40
     hay
    0.40
     concentrations
    0.40
     calculadora
    0.40
     alguien
    0.39
    POSITIVE LOGITS
    SqlServer
    0.41
    Weyl
    0.40
    oxane
    0.37
    ridate
    0.37
    ('"
    0.37
    äume
    0.37
    })$-
    0.36
     internazionale
    0.36
    ိန်
    0.35
    ብዙ
    0.35
    Act Density 0.000%

    No Known Activations