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

    Neuronpedia

    INDEX
    Explanations

    Reform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Helper
    -0.08
    texts
    -0.07
    	Version
    -0.06
     thoát
    -0.06
    Try
    -0.06
     hå
    -0.06
     �
    -0.06
    flashdata
    -0.06
    μ
    -0.06
    -ca
    -0.06
    POSITIVE LOGITS
     "]
    0.07
    Grant
    0.06
     feasible
    0.06
    awning
    0.06
     güvenlik
    0.06
    _cutoff
    0.06
     складі
    0.06
     blowjob
    0.06
     Народ
    0.06
    sson
    0.06
    Act Density 0.000%

    No Known Activations