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

    Neuronpedia

    INDEX
    Explanations

    Starfleet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PRF
    0.44
     câncer
    0.43
     நின்
    0.42
     роман
    0.41
     PFS
    0.39
     pras
    0.39
     Praia
    0.39
    告
    0.39
    PRA
    0.39
     пра
    0.38
    POSITIVE LOGITS
     Fleisch
    0.50
    fle
    0.44
    Fle
    0.42
    fleet
    0.39
    float
    0.38
    Single
    0.38
    SINGLE
    0.37
    ifilm
    0.37
    tn
    0.36
    astos
    0.35
    Act Density 0.000%

    No Known Activations