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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    get
    -0.07
    Raised
    -0.07
    vw
    -0.06
    ponent
    -0.06
    GET
    -0.06
    	now
    -0.06
    ным
    -0.06
    ôt
    -0.06
    ––
    -0.06
     \@
    -0.06
    POSITIVE LOGITS
     titleLabel
    0.07
     Brooke
    0.07
     bourgeoisie
    0.07
    (pin
    0.06
    UIStoryboardSegue
    0.06
    LOOD
    0.06
     Linked
    0.06
     �
    0.06
    एक
    0.06
     СРСР
    0.06
    Act Density 0.000%

    No Known Activations