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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CAUSED
    -0.07
    belongsTo
    -0.07
    "But
    -0.07
     ise
    -0.06
     خاص
    -0.06
     Containers
    -0.06
    POOL
    -0.06
    apore
    -0.06
    吾
    -0.06
     Overrides
    -0.06
    POSITIVE LOGITS
     sizable
    0.07
     conscient
    0.06
    -UA
    0.06
     рів
    0.06
    .Port
    0.06
     PSP
    0.06
    rik
    0.06
     frustrations
    0.06
     För
    0.06
    ddl
    0.06
    Act Density 0.017%

    No Known Activations