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

    Neuronpedia

    INDEX
    Explanations

    snippets of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blacks
    -0.06
     facets
    -0.06
    ode
    -0.06
    매
    -0.06
     Medium
    -0.06
    öyle
    -0.06
    IEEE
    -0.06
    Administr
    -0.06
    忆
    -0.06
    _offer
    -0.06
    POSITIVE LOGITS
    �
    0.07
    antidad
    0.07
    cheduling
    0.07
    .sell
    0.06
    >'+
    0.06
     Disconnect
    0.06
     caregivers
    0.06
    เ
    0.06
    pearance
    0.06
    %H
    0.06
    Act Density 0.110%

    No Known Activations