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

    Neuronpedia

    INDEX
    Explanations

    Inclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    572
    -0.07
     footsteps
    -0.07
     opponents
    -0.06
    gerald
    -0.06
    568
    -0.06
     habitat
    -0.06
     hex
    -0.06
     shows
    -0.06
    _Project
    -0.06
    MP
    -0.06
    POSITIVE LOGITS
    เคย
    0.07
     쉽
    0.07
     BBC
    0.06
    (u
    0.06
     french
    0.06
     �
    0.06
    Prefix
    0.06
     nightlife
    0.06
     wholesome
    0.06
    퓨
    0.06
    Act Density 0.002%

    No Known Activations