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

    Neuronpedia

    INDEX
    Explanations

    drop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ctrl
    -0.07
            
↵
    -0.06
                            ↵
    -0.06
    債
    -0.06
    ;\
    -0.06
     pdata
    -0.06
     Dean
    -0.06
    捐款
    -0.06
    超强
    -0.06
    >In
    -0.06
    POSITIVE LOGITS
    _AMD
    0.07
    .ai
    0.07
     Protest
    0.07
    玩意
    0.07
     име
    0.07
    itet
    0.07
    ṟ
    0.07
    lichen
    0.07
     feared
    0.07
     Credentials
    0.07
    Act Density 0.001%

    No Known Activations