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

    Neuronpedia

    INDEX
    Explanations

    end of if statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }]);
    -0.93
    }*/
    -0.91
    }}=\
    -0.91
    }?>
    -0.88
    ]]
    -0.85
     stuck
    -0.84
    )}}
    -0.79
    PushButton
    -0.79
    "];
    -0.79
     mendatang
    -0.79
    POSITIVE LOGITS
     but
    1.71
    ";}
    1.17
    But
    1.16
     แต่
    1.16
     But
    1.06
    else
    1.05
     nhưng
    1.05
    <h3>
    1.05
     BUT
    1.04
     however
    1.02
    Act Density 0.030%

    No Known Activations