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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paradise
    -0.07
    arming
    -0.07
     swarm
    -0.06
     brew
    -0.06
     Crime
    -0.06
    油
    -0.06
    /library
    -0.06
     standing
    -0.06
    vestment
    -0.06
     holdings
    -0.06
    POSITIVE LOGITS
    SmartyHeaderCode
    0.06
    .getID
    0.06
     tách
    0.06
    OCK
    0.06
    切
    0.06
    _IB
    0.06
    _mp
    0.06
    utos
    0.06
     біля
    0.06
    cele
    0.06
    Act Density 0.061%

    No Known Activations