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

    Neuronpedia

    INDEX
    Explanations

    protocol, particles, control, position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoffe
    0.45
    akta
    0.40
    ieres
    0.38
    اب
    0.38
    ace
    0.38
    Getter
    0.38
    stan
    0.38
    Result
    0.38
    actory
    0.37
    жу
    0.36
    POSITIVE LOGITS
     Intelli
    0.46
     dependen
    0.45
     kami
    0.44
     Arden
    0.44
     Anchorage
    0.43
     CIF
    0.42
     dependent
    0.42
     Intelligent
    0.42
     permisos
    0.42
     kWh
    0.41
    Act Density 0.000%

    No Known Activations