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

    Neuronpedia

    INDEX
    Explanations

    need to or need for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شرطونه
    0.39
    와의
    0.36
     صارت
    0.36
    йн
    0.36
     misused
    0.36
     থাকিলে
    0.35
    <0x0D>
    0.34
     Bedingungen
    0.33
     Conditions
    0.33
     expectancy
    0.33
    POSITIVE LOGITS
     to
    0.64
     need
    0.61
     bisogno
    0.54
     bantuan
    0.52
    need
    0.50
    NEED
    0.48
     desperately
    0.47
     dringend
    0.46
     help
    0.46
     necesidad
    0.46
    Act Density 0.034%

    No Known Activations