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

    Neuronpedia

    INDEX
    Explanations

    Star Trek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sensor
    -0.08
     หม
    -0.07
    _ENTRY
    -0.07
    建设
    -0.07
    ится
    -0.06
    _layer
    -0.06
     aktar
    -0.06
    (network
    -0.06
    (target
    -0.06
    ити
    -0.06
    POSITIVE LOGITS
     Laz
    0.06
    lost
    0.06
     Afr
    0.06
    Everybody
    0.06
     precarious
    0.06
     Aless
    0.06
    ekli
    0.06
     vom
    0.06
    éné
    0.05
    ields
    0.05
    Act Density 0.031%

    No Known Activations