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

    Neuronpedia

    INDEX
    Explanations

    denied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    函数
    -0.07
    -second
    -0.06
     formed
    -0.06
    -light
    -0.06
     patient
    -0.06
    iais
    -0.06
     oath
    -0.06
     boiling
    -0.06
     tố
    -0.06
     Proper
    -0.06
    POSITIVE LOGITS
    .person
    0.07
     Dagger
    0.07
     FontAwesome
    0.06
    =f
    0.06
     �
    0.06
    ='{$
    0.06
     Gef
    0.06
     Север
    0.06
     clo
    0.06
    rena
    0.06
    Act Density 0.025%

    No Known Activations