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

    Neuronpedia

    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    branches
    -0.07
     λ
    -0.07
    786
    -0.07
     Mixer
    -0.07
    Order
    -0.06
     greetings
    -0.06
    ATTERY
    -0.06
     mutable
    -0.06
    INTER
    -0.06
    illegal
    -0.06
    POSITIVE LOGITS
     force
    0.08
    ��
    0.07
     forces
    0.07
    .tt
    0.07
    ----------</
    0.07
    .Constants
    0.06
    된다
    0.06
    Mark
    0.06
     consectetur
    0.06
    ufig
    0.06
    Act Density 0.008%

    No Known Activations