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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heat
    -0.08
    endir
    -0.07
     Kem
    -0.06
     sizable
    -0.06
     Jame
    -0.06
    ковод
    -0.06
    níkem
    -0.06
    _moves
    -0.06
     Ch
    -0.06
     gradients
    -0.06
    POSITIVE LOGITS
    (mapStateToProps
    0.07
     ""
↵
    0.06
    	UP
    0.06
    .Stdout
    0.06
    (eval
    0.06
    �
    0.06
     máme
    0.06
    Оп
    0.06
    owering
    0.06
     astonishing
    0.06
    Act Density 0.010%

    No Known Activations