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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brate
    -0.07
     spokesperson
    -0.07
    Gtk
    -0.07
    credentials
    -0.07
     spokeswoman
    -0.06
     spokesman
    -0.06
    thora
    -0.06
     Над
    -0.06
     перевір
    -0.06
    loat
    -0.06
    POSITIVE LOGITS
     note
    0.06
     tome
    0.06
    esco
    0.06
     WN
    0.06
     onClick
    0.06
    emony
    0.06
     primitives
    0.06
    employed
    0.06
     WTO
    0.06
    �
    0.05
    Act Density 0.002%

    No Known Activations