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

    Neuronpedia

    INDEX
    Explanations

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laurel
    -0.06
    Rs
    -0.06
    ̣c
    -0.05
     Sof
    -0.05
    ماری
    -0.05
    RC
    -0.05
    elyn
    -0.05
    _rows
    -0.05
    ₃
    -0.05
     fascism
    -0.05
    POSITIVE LOGITS
     опас
    0.07
     unwilling
    0.07
    illed
    0.07
     měli
    0.07
    iffies
    0.07
    IPAddress
    0.07
    due
    0.07
    .xyz
    0.07
    AZ
    0.07
    .Atomic
    0.07
    Act Density 0.005%

    No Known Activations