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

    Neuronpedia

    INDEX
    Explanations

    _delete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [table
    -0.07
     hf
    -0.07
     LRV
    -0.07
     �
    -0.07
     Crus
    -0.07
    .toFixed
    -0.07
     возраста
    -0.07
     Lana
    -0.07
     recruits
    -0.07
    نین
    -0.07
    POSITIVE LOGITS
    �
    0.06
    URAL
    0.06
    ποι
    0.06
     worked
    0.06
     tercih
    0.06
    πι
    0.06
    urally
    0.06
     banging
    0.06
    ğit
    0.06
     integral
    0.06
    Act Density 0.002%

    No Known Activations