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

    Neuronpedia

    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motivational
    -0.09
     psychological
    -0.08
    urrican
    -0.08
     Psychological
    -0.08
     sitcom
    -0.08
    fade
    -0.08
    confirmation
    -0.08
     hitch
    -0.08
    изоля
    -0.08
     inflación
    -0.08
    POSITIVE LOGITS
     ಬೀ
    0.08
     Asi
    0.07
    atic
    0.07
    Adder
    0.07
     ಪ್ರ
    0.07
    ンサー
    0.07
     veins
    0.07
    ಂತ
    0.07
    ರಾಗ
    0.07
    ರು
    0.07
    Act Density 0.007%

    No Known Activations