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

    Neuronpedia

    INDEX
    Explanations

    configuration file keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terve
    0.65
     тэ
    0.59
    ين
    0.55
     zoek
    0.55
    Repr
    0.55
     fejl
    0.54
     gesund
    0.54
     configFile
    0.54
    ν
    0.54
     ganhou
    0.53
    POSITIVE LOGITS
     a
    0.58
     rápid
    0.58
    0.56
     Aspen
    0.55
     Cedar
    0.54
     Tunnel
    0.54
     Copenhagen
    0.53
     Siemens
    0.52
     Coke
    0.52
     Doug
    0.52
    Act Density 0.000%

    No Known Activations