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

    Neuronpedia

    INDEX
    Explanations

    cool, awesome, amazing, fantastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delicately
    0.42
     unwelcome
    0.39
    delim
    0.39
    睗
    0.39
     ಫಲ
    0.38
     ಅಭ
    0.37
     delicate
    0.37
    STRAINT
    0.37
     تعليم
    0.37
    冗
    0.37
    POSITIVE LOGITS
     cool
    2.81
     awesome
    2.73
    cool
    2.58
     coolest
    2.39
    awesome
    2.36
    Awesome
    2.36
     Cool
    2.34
     Awesome
    2.34
    Cool
    2.31
     COOL
    2.11
    Act Density 0.088%

    No Known Activations