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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plants
    -0.07
     trừ
    -0.07
    hari
    -0.07
    dere
    -0.06
     subtitle
    -0.06
     voiture
    -0.06
    filled
    -0.06
    -phone
    -0.06
     setw
    -0.06
    itution
    -0.06
    POSITIVE LOGITS
    .fn
    0.07
    _inventory
    0.07
    :'',
    0.06
    Callback
    0.06
    .engine
    0.06
     нед
    0.06
     Jeans
    0.06
    .POST
    0.06
     Volkswagen
    0.06
     ICollection
    0.06
    Act Density 0.026%

    No Known Activations