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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _con
    -0.07
     calcular
    -0.07
    3
    -0.07
     Con
    -0.07
    .say
    -0.07
    ekim
    -0.07
     vaguely
    -0.06
     ou
    -0.06
    _Con
    -0.06
    stractions
    -0.06
    POSITIVE LOGITS
    “Well
    0.06
    一种
    0.06
    “My
    0.06
     setTitle
    0.06
     bill
    0.05
     perpetrated
    0.05
    IEW
    0.05
     авг
    0.05
    NameValuePair
    0.05
    .toolbar
    0.05
    Act Density 0.747%

    No Known Activations