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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muster
    -0.07
    (properties
    -0.06
     мер
    -0.06
     encourages
    -0.06
     mobil
    -0.06
    .school
    -0.06
    .Upload
    -0.06
    <<"
    -0.06
     positive
    -0.06
    اها
    -0.06
    POSITIVE LOGITS
     Pepsi
    0.07
    .gl
    0.06
     TI
    0.06
    .terminate
    0.06
     fantasy
    0.06
     pkg
    0.06
    .img
    0.06
     실�
    0.06
     villains
    0.06
    _hero
    0.06
    Act Density 0.014%

    No Known Activations