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

    Neuronpedia

    INDEX
    Explanations

    Code syntax components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Free
    -0.06
    Atl
    -0.06
    ODEV
    -0.06
    +'/
    -0.06
     harmed
    -0.06
    apphire
    -0.06
    atıcı
    -0.06
    generated
    -0.06
    structions
    -0.06
    !("{
    -0.06
    POSITIVE LOGITS
     underage
    0.07
    ~":"
    0.07
    .sdk
    0.06
     Holds
    0.06
    "H
    0.06
     Nurse
    0.06
    @pytest
    0.06
     جون
    0.06
     interrogation
    0.06
    aret
    0.06
    Act Density 0.011%

    No Known Activations