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

    Neuronpedia

    INDEX
    Explanations

    chemical characteristics and exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Force
    0.48
    force
    0.47
    FORCE
    0.45
     çöze
    0.45
     बराबर
    0.43
     භාවිත
    0.43
    𝗘
    0.43
     проблему
    0.43
     éxito
    0.43
    كيف
    0.43
    POSITIVE LOGITS
     characteristics
    0.61
     exploring
    0.59
     fascinating
    0.56
     unique
    0.55
     exploration
    0.55
     explor
    0.55
     explores
    0.54
     explore
    0.53
     distinctive
    0.53
     intriguing
    0.52
    Act Density 0.000%

    No Known Activations